Qwen/Qwen2-72B

Explore Qwen/Qwen2-72B: model specifications, capabilities, benchmark results, platform pricing and original sources.

huggingface/Qwen/Qwen2-72B

Specifications & capabilities

Input
text
Output
text
Published model ID
Qwen2-72B

Evaluations

1–20 / 54

LLM Stats · GitHub archive

0.901

source id
llmStatsArchive
leaderboard name
CMMLU · Normalized (reported)
dimension
general
metric
CMMLU · Normalized (reported)
rank
1
aggregation scope
status
archived
license
CC-BY-4.0
direction
higherIsBetter
conditions
language
en
benchmark
name
CMMLU
language
en
modality
text
verified
false
max_score
1
categories
  • language
  • reasoning
  • general
created_at
2025-07-19T19:56:14.941108+00:00
paper_link
https://arxiv.org/abs/2306.09212
updated_at
2025-07-19T19:56:14.941108+00:00
description
CMMLU (Chinese Massive Multitask Language Understanding) is a comprehensive Chinese benchmark that evaluates the knowledge and reasoning capabilities of large language models across 67 different subject topics. The benchmark covers natural sciences, social sciences, engineering, and humanities with multiple-choice questions ranging from basic to advanced professional levels.
benchmark_id
cmmlu
multilingual
true
analysis_method
Accuracy
is_self_reported
true
verified_by_llmstats
false
attribution
Jonathan Chavez Tamales and LLM Stats contributors (copyright 2024 jc); TensorTrace structures original results and derives scoped ranks.
license_url
https://creativecommons.org/licenses/by/4.0/
metric_kind
CMMLU · Normalized (reported)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
data/organizations/qwen/models/qwen2-72b-instruct/benchmarks.json
archive_kind
llmStats
evidence_url
https://huggingface.co/Qwen/Qwen2-72B
git_revision
872b75f63b8d853c46ed17856424029a0c47b1d2
published_at
2025-10-24T17:47:59Z
snapshot_date
2025-10-24T17:47:59Z
source_revision
6e27aa41f51fa8cb327602349240077d1c7acae9fead8ba2f07db0d549927ddc
publisher_anchor
qwen/qwen2-72b-instruct
metric_population
1
current_catalog_url
https://llm-stats.com/
benchmark_evaluation
true
source model id
qwen2-72b-instruct
Original result ↗

LLM Stats · GitHub archive

0.901

source id
llmStatsArchive
leaderboard name
CMMLU · Raw
dimension
general
metric
CMMLU · Raw
rank
1
aggregation scope
status
archived
license
CC-BY-4.0
direction
higherIsBetter
conditions
language
en
benchmark
name
CMMLU
language
en
modality
text
verified
false
max_score
1
categories
  • language
  • reasoning
  • general
created_at
2025-07-19T19:56:14.941108+00:00
paper_link
https://arxiv.org/abs/2306.09212
updated_at
2025-07-19T19:56:14.941108+00:00
description
CMMLU (Chinese Massive Multitask Language Understanding) is a comprehensive Chinese benchmark that evaluates the knowledge and reasoning capabilities of large language models across 67 different subject topics. The benchmark covers natural sciences, social sciences, engineering, and humanities with multiple-choice questions ranging from basic to advanced professional levels.
benchmark_id
cmmlu
multilingual
true
analysis_method
Accuracy
is_self_reported
true
verified_by_llmstats
false
attribution
Jonathan Chavez Tamales and LLM Stats contributors (copyright 2024 jc); TensorTrace structures original results and derives scoped ranks.
license_url
https://creativecommons.org/licenses/by/4.0/
metric_kind
CMMLU · Raw
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
data/organizations/qwen/models/qwen2-72b-instruct/benchmarks.json
archive_kind
llmStats
evidence_url
https://huggingface.co/Qwen/Qwen2-72B
git_revision
872b75f63b8d853c46ed17856424029a0c47b1d2
published_at
2025-10-24T17:47:59Z
snapshot_date
2025-10-24T17:47:59Z
source_revision
6e27aa41f51fa8cb327602349240077d1c7acae9fead8ba2f07db0d549927ddc
publisher_anchor
qwen/qwen2-72b-instruct
metric_population
1
current_catalog_url
https://llm-stats.com/
benchmark_evaluation
true
source model id
qwen2-72b-instruct
Original result ↗

LLM Stats · GitHub archive

0.876

source id
llmStatsArchive
leaderboard name
HellaSwag · Raw
dimension
general
metric
HellaSwag · Raw
rank
1
aggregation scope
status
archived
license
CC-BY-4.0
direction
higherIsBetter
conditions
language
en
benchmark
name
HellaSwag
language
en
modality
text
verified
false
max_score
1
categories
  • reasoning
created_at
2025-07-19T19:56:11.145630+00:00
paper_link
https://arxiv.org/abs/1905.07830
updated_at
2025-07-19T19:56:11.145630+00:00
description
A challenging commonsense natural language inference dataset that uses Adversarial Filtering to create questions trivial for humans (>95% accuracy) but difficult for state-of-the-art models, requiring completion of sentence endings based on physical situations and everyday activities
benchmark_id
hellaswag
multilingual
false
analysis_method
Accuracy
is_self_reported
true
verified_by_llmstats
false
attribution
Jonathan Chavez Tamales and LLM Stats contributors (copyright 2024 jc); TensorTrace structures original results and derives scoped ranks.
license_url
https://creativecommons.org/licenses/by/4.0/
metric_kind
HellaSwag · Raw
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
data/organizations/qwen/models/qwen2-72b-instruct/benchmarks.json
archive_kind
llmStats
evidence_url
https://huggingface.co/Qwen/Qwen2-72B
git_revision
872b75f63b8d853c46ed17856424029a0c47b1d2
published_at
2025-10-24T17:47:59Z
snapshot_date
2025-10-24T17:47:59Z
source_revision
6e27aa41f51fa8cb327602349240077d1c7acae9fead8ba2f07db0d549927ddc
publisher_anchor
qwen/qwen2-72b-instruct
metric_population
1
current_catalog_url
https://llm-stats.com/
benchmark_evaluation
true
source model id
qwen2-72b-instruct
Original result ↗

LLM Stats · GitHub archive

0.876

source id
llmStatsArchive
leaderboard name
HellaSwag · Normalized (reported)
dimension
general
metric
HellaSwag · Normalized (reported)
rank
1
aggregation scope
status
archived
license
CC-BY-4.0
direction
higherIsBetter
conditions
language
en
benchmark
name
HellaSwag
language
en
modality
text
verified
false
max_score
1
categories
  • reasoning
created_at
2025-07-19T19:56:11.145630+00:00
paper_link
https://arxiv.org/abs/1905.07830
updated_at
2025-07-19T19:56:11.145630+00:00
description
A challenging commonsense natural language inference dataset that uses Adversarial Filtering to create questions trivial for humans (>95% accuracy) but difficult for state-of-the-art models, requiring completion of sentence endings based on physical situations and everyday activities
benchmark_id
hellaswag
multilingual
false
analysis_method
Accuracy
is_self_reported
true
verified_by_llmstats
false
attribution
Jonathan Chavez Tamales and LLM Stats contributors (copyright 2024 jc); TensorTrace structures original results and derives scoped ranks.
license_url
https://creativecommons.org/licenses/by/4.0/
metric_kind
HellaSwag · Normalized (reported)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
data/organizations/qwen/models/qwen2-72b-instruct/benchmarks.json
archive_kind
llmStats
evidence_url
https://huggingface.co/Qwen/Qwen2-72B
git_revision
872b75f63b8d853c46ed17856424029a0c47b1d2
published_at
2025-10-24T17:47:59Z
snapshot_date
2025-10-24T17:47:59Z
source_revision
6e27aa41f51fa8cb327602349240077d1c7acae9fead8ba2f07db0d549927ddc
publisher_anchor
qwen/qwen2-72b-instruct
metric_population
1
current_catalog_url
https://llm-stats.com/
benchmark_evaluation
true
source model id
qwen2-72b-instruct
Original result ↗

LLM Stats · GitHub archive

0.851

source id
llmStatsArchive
leaderboard name
Winogrande · Normalized (reported)
dimension
general
metric
Winogrande · Normalized (reported)
rank
1
aggregation scope
status
archived
license
CC-BY-4.0
direction
higherIsBetter
conditions
language
en
benchmark
name
Winogrande
language
en
modality
text
verified
false
max_score
1
categories
  • reasoning
  • language
created_at
2025-07-19T19:56:11.370408+00:00
paper_link
https://arxiv.org/abs/1907.10641
updated_at
2025-07-19T19:56:11.370408+00:00
description
WinoGrande: An Adversarial Winograd Schema Challenge at Scale. A large-scale dataset of 44,000 pronoun resolution problems designed to test machine commonsense reasoning. Uses adversarial filtering to reduce spurious biases and provides a more robust evaluation of whether AI systems truly understand commonsense or exploit statistical shortcuts. Current best AI methods achieve 59.4-79.1% accuracy, significantly below human performance of 94.0%.
benchmark_id
winogrande
multilingual
false
analysis_method
Accuracy
is_self_reported
true
verified_by_llmstats
false
attribution
Jonathan Chavez Tamales and LLM Stats contributors (copyright 2024 jc); TensorTrace structures original results and derives scoped ranks.
license_url
https://creativecommons.org/licenses/by/4.0/
metric_kind
Winogrande · Normalized (reported)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
data/organizations/qwen/models/qwen2-72b-instruct/benchmarks.json
archive_kind
llmStats
evidence_url
https://huggingface.co/Qwen/Qwen2-72B
git_revision
872b75f63b8d853c46ed17856424029a0c47b1d2
published_at
2025-10-24T17:47:59Z
snapshot_date
2025-10-24T17:47:59Z
source_revision
6e27aa41f51fa8cb327602349240077d1c7acae9fead8ba2f07db0d549927ddc
publisher_anchor
qwen/qwen2-72b-instruct
metric_population
1
current_catalog_url
https://llm-stats.com/
benchmark_evaluation
true
source model id
qwen2-72b-instruct
Original result ↗

LLM Stats · GitHub archive

0.851

source id
llmStatsArchive
leaderboard name
Winogrande · Raw
dimension
general
metric
Winogrande · Raw
rank
1
aggregation scope
status
archived
license
CC-BY-4.0
direction
higherIsBetter
conditions
language
en
benchmark
name
Winogrande
language
en
modality
text
verified
false
max_score
1
categories
  • reasoning
  • language
created_at
2025-07-19T19:56:11.370408+00:00
paper_link
https://arxiv.org/abs/1907.10641
updated_at
2025-07-19T19:56:11.370408+00:00
description
WinoGrande: An Adversarial Winograd Schema Challenge at Scale. A large-scale dataset of 44,000 pronoun resolution problems designed to test machine commonsense reasoning. Uses adversarial filtering to reduce spurious biases and provides a more robust evaluation of whether AI systems truly understand commonsense or exploit statistical shortcuts. Current best AI methods achieve 59.4-79.1% accuracy, significantly below human performance of 94.0%.
benchmark_id
winogrande
multilingual
false
analysis_method
Accuracy
is_self_reported
true
verified_by_llmstats
false
attribution
Jonathan Chavez Tamales and LLM Stats contributors (copyright 2024 jc); TensorTrace structures original results and derives scoped ranks.
license_url
https://creativecommons.org/licenses/by/4.0/
metric_kind
Winogrande · Raw
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
data/organizations/qwen/models/qwen2-72b-instruct/benchmarks.json
archive_kind
llmStats
evidence_url
https://huggingface.co/Qwen/Qwen2-72B
git_revision
872b75f63b8d853c46ed17856424029a0c47b1d2
published_at
2025-10-24T17:47:59Z
snapshot_date
2025-10-24T17:47:59Z
source_revision
6e27aa41f51fa8cb327602349240077d1c7acae9fead8ba2f07db0d549927ddc
publisher_anchor
qwen/qwen2-72b-instruct
metric_population
1
current_catalog_url
https://llm-stats.com/
benchmark_evaluation
true
source model id
qwen2-72b-instruct
Original result ↗

LLM Stats · GitHub archive

0.838

source id
llmStatsArchive
leaderboard name
C-Eval · Normalized (reported)
dimension
general
metric
C-Eval · Normalized (reported)
rank
1
aggregation scope
status
archived
license
CC-BY-4.0
direction
higherIsBetter
conditions
language
en
benchmark
name
C-Eval
language
en
modality
text
verified
false
max_score
1
categories
  • general
  • reasoning
created_at
2025-07-19T19:56:11.917478+00:00
paper_link
https://arxiv.org/abs/2305.08322
updated_at
2025-07-19T19:56:11.917478+00:00
description
C-Eval is a comprehensive Chinese evaluation suite designed to assess advanced knowledge and reasoning abilities of foundation models in a Chinese context. It comprises 13,948 multiple-choice questions across 52 diverse disciplines spanning humanities, science, and engineering, with four difficulty levels: middle school, high school, college, and professional. The benchmark includes C-Eval Hard, a subset of very challenging subjects requiring advanced reasoning abilities.
benchmark_id
c-eval
multilingual
true
analysis_method
Accuracy
is_self_reported
true
verified_by_llmstats
false
attribution
Jonathan Chavez Tamales and LLM Stats contributors (copyright 2024 jc); TensorTrace structures original results and derives scoped ranks.
license_url
https://creativecommons.org/licenses/by/4.0/
metric_kind
C-Eval · Normalized (reported)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
data/organizations/qwen/models/qwen2-72b-instruct/benchmarks.json
archive_kind
llmStats
evidence_url
https://huggingface.co/Qwen/Qwen2-72B
git_revision
872b75f63b8d853c46ed17856424029a0c47b1d2
published_at
2025-10-24T17:47:59Z
snapshot_date
2025-10-24T17:47:59Z
source_revision
6e27aa41f51fa8cb327602349240077d1c7acae9fead8ba2f07db0d549927ddc
publisher_anchor
qwen/qwen2-72b-instruct
metric_population
2
current_catalog_url
https://llm-stats.com/
benchmark_evaluation
true
source model id
qwen2-72b-instruct
Original result ↗

LLM Stats · GitHub archive

0.838

source id
llmStatsArchive
leaderboard name
C-Eval · Raw
dimension
general
metric
C-Eval · Raw
rank
1
aggregation scope
status
archived
license
CC-BY-4.0
direction
higherIsBetter
conditions
language
en
benchmark
name
C-Eval
language
en
modality
text
verified
false
max_score
1
categories
  • general
  • reasoning
created_at
2025-07-19T19:56:11.917478+00:00
paper_link
https://arxiv.org/abs/2305.08322
updated_at
2025-07-19T19:56:11.917478+00:00
description
C-Eval is a comprehensive Chinese evaluation suite designed to assess advanced knowledge and reasoning abilities of foundation models in a Chinese context. It comprises 13,948 multiple-choice questions across 52 diverse disciplines spanning humanities, science, and engineering, with four difficulty levels: middle school, high school, college, and professional. The benchmark includes C-Eval Hard, a subset of very challenging subjects requiring advanced reasoning abilities.
benchmark_id
c-eval
multilingual
true
analysis_method
Accuracy
is_self_reported
true
verified_by_llmstats
false
attribution
Jonathan Chavez Tamales and LLM Stats contributors (copyright 2024 jc); TensorTrace structures original results and derives scoped ranks.
license_url
https://creativecommons.org/licenses/by/4.0/
metric_kind
C-Eval · Raw
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
data/organizations/qwen/models/qwen2-72b-instruct/benchmarks.json
archive_kind
llmStats
evidence_url
https://huggingface.co/Qwen/Qwen2-72B
git_revision
872b75f63b8d853c46ed17856424029a0c47b1d2
published_at
2025-10-24T17:47:59Z
snapshot_date
2025-10-24T17:47:59Z
source_revision
6e27aa41f51fa8cb327602349240077d1c7acae9fead8ba2f07db0d549927ddc
publisher_anchor
qwen/qwen2-72b-instruct
metric_population
2
current_catalog_url
https://llm-stats.com/
benchmark_evaluation
true
source model id
qwen2-72b-instruct
Original result ↗

LLM Stats · GitHub archive

0.802

source id
llmStatsArchive
leaderboard name
MBPP · Normalized (reported)
dimension
general
metric
MBPP · Normalized (reported)
rank
1
aggregation scope
status
archived
license
CC-BY-4.0
direction
higherIsBetter
conditions
language
en
benchmark
name
MBPP
language
en
modality
text
verified
false
max_score
100
categories
  • reasoning
  • general
created_at
2025-07-19T19:56:13.453370+00:00
paper_link
https://arxiv.org/abs/2108.07732
updated_at
2025-07-19T19:56:13.453370+00:00
description
MBPP (Mostly Basic Python Problems) is a benchmark of 974 crowd-sourced Python programming problems designed to be solvable by entry-level programmers. Each problem consists of a task description, code solution, and 3 automated test cases covering programming fundamentals and standard library functionality.
benchmark_id
mbpp
multilingual
false
analysis_method
Pass@1
is_self_reported
true
verified_by_llmstats
false
attribution
Jonathan Chavez Tamales and LLM Stats contributors (copyright 2024 jc); TensorTrace structures original results and derives scoped ranks.
license_url
https://creativecommons.org/licenses/by/4.0/
metric_kind
MBPP · Normalized (reported)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
data/organizations/qwen/models/qwen2-72b-instruct/benchmarks.json
archive_kind
llmStats
evidence_url
https://huggingface.co/Qwen/Qwen2-72B
git_revision
872b75f63b8d853c46ed17856424029a0c47b1d2
published_at
2025-10-24T17:47:59Z
snapshot_date
2025-10-24T17:47:59Z
source_revision
6e27aa41f51fa8cb327602349240077d1c7acae9fead8ba2f07db0d549927ddc
publisher_anchor
qwen/qwen2-72b-instruct
metric_population
3
current_catalog_url
https://llm-stats.com/
benchmark_evaluation
true
source model id
qwen2-72b-instruct
Original result ↗

LLM Stats · GitHub archive

0.802

source id
llmStatsArchive
leaderboard name
MBPP · Raw
dimension
general
metric
MBPP · Raw
rank
1
aggregation scope
status
archived
license
CC-BY-4.0
direction
higherIsBetter
conditions
language
en
benchmark
name
MBPP
language
en
modality
text
verified
false
max_score
100
categories
  • reasoning
  • general
created_at
2025-07-19T19:56:13.453370+00:00
paper_link
https://arxiv.org/abs/2108.07732
updated_at
2025-07-19T19:56:13.453370+00:00
description
MBPP (Mostly Basic Python Problems) is a benchmark of 974 crowd-sourced Python programming problems designed to be solvable by entry-level programmers. Each problem consists of a task description, code solution, and 3 automated test cases covering programming fundamentals and standard library functionality.
benchmark_id
mbpp
multilingual
false
analysis_method
Pass@1
is_self_reported
true
verified_by_llmstats
false
attribution
Jonathan Chavez Tamales and LLM Stats contributors (copyright 2024 jc); TensorTrace structures original results and derives scoped ranks.
license_url
https://creativecommons.org/licenses/by/4.0/
metric_kind
MBPP · Raw
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
data/organizations/qwen/models/qwen2-72b-instruct/benchmarks.json
archive_kind
llmStats
evidence_url
https://huggingface.co/Qwen/Qwen2-72B
git_revision
872b75f63b8d853c46ed17856424029a0c47b1d2
published_at
2025-10-24T17:47:59Z
snapshot_date
2025-10-24T17:47:59Z
source_revision
6e27aa41f51fa8cb327602349240077d1c7acae9fead8ba2f07db0d549927ddc
publisher_anchor
qwen/qwen2-72b-instruct
metric_population
3
current_catalog_url
https://llm-stats.com/
benchmark_evaluation
true
source model id
qwen2-72b-instruct
Original result ↗

LLM Stats · GitHub archive

0.444

source id
llmStatsArchive
leaderboard name
TheoremQA · Raw
dimension
general
metric
TheoremQA · Raw
rank
1
aggregation scope
status
archived
license
CC-BY-4.0
direction
higherIsBetter
conditions
language
en
benchmark
name
TheoremQA
language
en
modality
text
verified
false
max_score
1
categories
  • math
  • reasoning
  • physics
  • finance
created_at
2025-07-19T19:56:14.479157+00:00
paper_link
https://arxiv.org/abs/2305.12524
updated_at
2025-07-19T19:56:14.479157+00:00
description
A theorem-driven question answering dataset containing 800 high-quality questions covering 350+ theorems from Math, Physics, EE&CS, and Finance. Designed to evaluate AI models' capabilities to apply theorems to solve challenging university-level science problems.
benchmark_id
theoremqa
multilingual
false
analysis_method
Accuracy
is_self_reported
true
verified_by_llmstats
false
attribution
Jonathan Chavez Tamales and LLM Stats contributors (copyright 2024 jc); TensorTrace structures original results and derives scoped ranks.
license_url
https://creativecommons.org/licenses/by/4.0/
metric_kind
TheoremQA · Raw
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
data/organizations/qwen/models/qwen2-72b-instruct/benchmarks.json
archive_kind
llmStats
evidence_url
https://huggingface.co/Qwen/Qwen2-72B
git_revision
872b75f63b8d853c46ed17856424029a0c47b1d2
published_at
2025-10-24T17:47:59Z
snapshot_date
2025-10-24T17:47:59Z
source_revision
6e27aa41f51fa8cb327602349240077d1c7acae9fead8ba2f07db0d549927ddc
publisher_anchor
qwen/qwen2-72b-instruct
metric_population
2
current_catalog_url
https://llm-stats.com/
benchmark_evaluation
true
source model id
qwen2-72b-instruct
Original result ↗

LLM Stats · GitHub archive

0.444

source id
llmStatsArchive
leaderboard name
TheoremQA · Normalized (reported)
dimension
general
metric
TheoremQA · Normalized (reported)
rank
1
aggregation scope
status
archived
license
CC-BY-4.0
direction
higherIsBetter
conditions
language
en
benchmark
name
TheoremQA
language
en
modality
text
verified
false
max_score
1
categories
  • math
  • reasoning
  • physics
  • finance
created_at
2025-07-19T19:56:14.479157+00:00
paper_link
https://arxiv.org/abs/2305.12524
updated_at
2025-07-19T19:56:14.479157+00:00
description
A theorem-driven question answering dataset containing 800 high-quality questions covering 350+ theorems from Math, Physics, EE&CS, and Finance. Designed to evaluate AI models' capabilities to apply theorems to solve challenging university-level science problems.
benchmark_id
theoremqa
multilingual
false
analysis_method
Accuracy
is_self_reported
true
verified_by_llmstats
false
attribution
Jonathan Chavez Tamales and LLM Stats contributors (copyright 2024 jc); TensorTrace structures original results and derives scoped ranks.
license_url
https://creativecommons.org/licenses/by/4.0/
metric_kind
TheoremQA · Normalized (reported)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
data/organizations/qwen/models/qwen2-72b-instruct/benchmarks.json
archive_kind
llmStats
evidence_url
https://huggingface.co/Qwen/Qwen2-72B
git_revision
872b75f63b8d853c46ed17856424029a0c47b1d2
published_at
2025-10-24T17:47:59Z
snapshot_date
2025-10-24T17:47:59Z
source_revision
6e27aa41f51fa8cb327602349240077d1c7acae9fead8ba2f07db0d549927ddc
publisher_anchor
qwen/qwen2-72b-instruct
metric_population
2
current_catalog_url
https://llm-stats.com/
benchmark_evaluation
true
source model id
qwen2-72b-instruct
Original result ↗

LLM Stats · GitHub archive

0.824

source id
llmStatsArchive
leaderboard name
BBH · Raw
dimension
general
metric
BBH · Raw
rank
2
aggregation scope
status
archived
license
CC-BY-4.0
direction
higherIsBetter
conditions
language
en
benchmark
name
BBH
language
en
modality
text
verified
false
max_score
1
categories
  • reasoning
  • math
  • language
created_at
2025-07-19T19:56:13.031859+00:00
paper_link
https://arxiv.org/abs/2210.09261
updated_at
2025-07-19T19:56:13.031859+00:00
description
Big-Bench Hard (BBH) is a suite of 23 challenging tasks selected from BIG-Bench for which prior language model evaluations did not outperform the average human-rater. These tasks require multi-step reasoning across diverse domains including arithmetic, logical reasoning, reading comprehension, and commonsense reasoning. The benchmark was designed to test capabilities believed to be beyond current language models and focuses on evaluating complex reasoning skills including temporal understanding, spatial reasoning, causal understanding, and deductive logical reasoning.
benchmark_id
bbh
multilingual
false
analysis_method
Accuracy
is_self_reported
true
verified_by_llmstats
false
attribution
Jonathan Chavez Tamales and LLM Stats contributors (copyright 2024 jc); TensorTrace structures original results and derives scoped ranks.
license_url
https://creativecommons.org/licenses/by/4.0/
metric_kind
BBH · Raw
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
data/organizations/qwen/models/qwen2-72b-instruct/benchmarks.json
archive_kind
llmStats
evidence_url
https://huggingface.co/Qwen/Qwen2-72B
git_revision
872b75f63b8d853c46ed17856424029a0c47b1d2
published_at
2025-10-24T17:47:59Z
snapshot_date
2025-10-24T17:47:59Z
source_revision
6e27aa41f51fa8cb327602349240077d1c7acae9fead8ba2f07db0d549927ddc
publisher_anchor
qwen/qwen2-72b-instruct
metric_population
2
current_catalog_url
https://llm-stats.com/
benchmark_evaluation
true
source model id
qwen2-72b-instruct
Original result ↗

LLM Stats · GitHub archive

0.824

source id
llmStatsArchive
leaderboard name
BBH · Normalized (reported)
dimension
general
metric
BBH · Normalized (reported)
rank
2
aggregation scope
status
archived
license
CC-BY-4.0
direction
higherIsBetter
conditions
language
en
benchmark
name
BBH
language
en
modality
text
verified
false
max_score
1
categories
  • reasoning
  • math
  • language
created_at
2025-07-19T19:56:13.031859+00:00
paper_link
https://arxiv.org/abs/2210.09261
updated_at
2025-07-19T19:56:13.031859+00:00
description
Big-Bench Hard (BBH) is a suite of 23 challenging tasks selected from BIG-Bench for which prior language model evaluations did not outperform the average human-rater. These tasks require multi-step reasoning across diverse domains including arithmetic, logical reasoning, reading comprehension, and commonsense reasoning. The benchmark was designed to test capabilities believed to be beyond current language models and focuses on evaluating complex reasoning skills including temporal understanding, spatial reasoning, causal understanding, and deductive logical reasoning.
benchmark_id
bbh
multilingual
false
analysis_method
Accuracy
is_self_reported
true
verified_by_llmstats
false
attribution
Jonathan Chavez Tamales and LLM Stats contributors (copyright 2024 jc); TensorTrace structures original results and derives scoped ranks.
license_url
https://creativecommons.org/licenses/by/4.0/
metric_kind
BBH · Normalized (reported)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
data/organizations/qwen/models/qwen2-72b-instruct/benchmarks.json
archive_kind
llmStats
evidence_url
https://huggingface.co/Qwen/Qwen2-72B
git_revision
872b75f63b8d853c46ed17856424029a0c47b1d2
published_at
2025-10-24T17:47:59Z
snapshot_date
2025-10-24T17:47:59Z
source_revision
6e27aa41f51fa8cb327602349240077d1c7acae9fead8ba2f07db0d549927ddc
publisher_anchor
qwen/qwen2-72b-instruct
metric_population
2
current_catalog_url
https://llm-stats.com/
benchmark_evaluation
true
source model id
qwen2-72b-instruct
Original result ↗

LLM Stats · GitHub archive

0.79

source id
llmStatsArchive
leaderboard name
EvalPlus · Raw
dimension
general
metric
EvalPlus · Raw
rank
2
aggregation scope
status
archived
license
CC-BY-4.0
direction
higherIsBetter
conditions
language
en
benchmark
name
EvalPlus
language
en
modality
text
verified
false
max_score
100
categories
  • reasoning
  • code
created_at
2025-07-19T19:56:11.793176+00:00
paper_link
https://arxiv.org/abs/2305.01210
updated_at
2025-07-19T19:56:11.793176+00:00
description
A rigorous code synthesis evaluation framework that augments existing datasets with extensive test cases generated by LLM and mutation-based strategies to better assess functional correctness of generated code, including HumanEval+ with 80x more test cases
benchmark_id
evalplus
multilingual
false
analysis_method
Pass@1
is_self_reported
true
verified_by_llmstats
false
attribution
Jonathan Chavez Tamales and LLM Stats contributors (copyright 2024 jc); TensorTrace structures original results and derives scoped ranks.
license_url
https://creativecommons.org/licenses/by/4.0/
metric_kind
EvalPlus · Raw
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
data/organizations/qwen/models/qwen2-72b-instruct/benchmarks.json
archive_kind
llmStats
evidence_url
https://huggingface.co/Qwen/Qwen2-72B
git_revision
872b75f63b8d853c46ed17856424029a0c47b1d2
published_at
2025-10-24T17:47:59Z
snapshot_date
2025-10-24T17:47:59Z
source_revision
6e27aa41f51fa8cb327602349240077d1c7acae9fead8ba2f07db0d549927ddc
publisher_anchor
qwen/qwen2-72b-instruct
metric_population
3
current_catalog_url
https://llm-stats.com/
benchmark_evaluation
true
source model id
qwen2-72b-instruct
Original result ↗

LLM Stats · GitHub archive

0.79

source id
llmStatsArchive
leaderboard name
EvalPlus · Normalized (reported)
dimension
general
metric
EvalPlus · Normalized (reported)
rank
2
aggregation scope
status
archived
license
CC-BY-4.0
direction
higherIsBetter
conditions
language
en
benchmark
name
EvalPlus
language
en
modality
text
verified
false
max_score
100
categories
  • reasoning
  • code
created_at
2025-07-19T19:56:11.793176+00:00
paper_link
https://arxiv.org/abs/2305.01210
updated_at
2025-07-19T19:56:11.793176+00:00
description
A rigorous code synthesis evaluation framework that augments existing datasets with extensive test cases generated by LLM and mutation-based strategies to better assess functional correctness of generated code, including HumanEval+ with 80x more test cases
benchmark_id
evalplus
multilingual
false
analysis_method
Pass@1
is_self_reported
true
verified_by_llmstats
false
attribution
Jonathan Chavez Tamales and LLM Stats contributors (copyright 2024 jc); TensorTrace structures original results and derives scoped ranks.
license_url
https://creativecommons.org/licenses/by/4.0/
metric_kind
EvalPlus · Normalized (reported)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
data/organizations/qwen/models/qwen2-72b-instruct/benchmarks.json
archive_kind
llmStats
evidence_url
https://huggingface.co/Qwen/Qwen2-72B
git_revision
872b75f63b8d853c46ed17856424029a0c47b1d2
published_at
2025-10-24T17:47:59Z
snapshot_date
2025-10-24T17:47:59Z
source_revision
6e27aa41f51fa8cb327602349240077d1c7acae9fead8ba2f07db0d549927ddc
publisher_anchor
qwen/qwen2-72b-instruct
metric_population
3
current_catalog_url
https://llm-stats.com/
benchmark_evaluation
true
source model id
qwen2-72b-instruct
Original result ↗

LLM Stats · GitHub archive

0.548

source id
llmStatsArchive
leaderboard name
TruthfulQA · Raw
dimension
general
metric
TruthfulQA · Raw
rank
2
aggregation scope
status
archived
license
CC-BY-4.0
direction
higherIsBetter
conditions
language
en
benchmark
name
TruthfulQA
language
en
modality
text
verified
false
max_score
1
categories
  • general
  • reasoning
  • legal
  • healthcare
  • finance
created_at
2025-07-19T19:56:11.339268+00:00
paper_link
https://arxiv.org/abs/2109.07958
updated_at
2025-07-19T19:56:11.339268+00:00
description
TruthfulQA is a benchmark to measure whether language models are truthful in generating answers to questions. It comprises 817 questions that span 38 categories, including health, law, finance and politics. The questions are crafted such that some humans would answer falsely due to a false belief or misconception, testing models' ability to avoid generating false answers learned from human texts.
benchmark_id
truthfulqa
multilingual
false
analysis_method
Accuracy
is_self_reported
true
verified_by_llmstats
false
attribution
Jonathan Chavez Tamales and LLM Stats contributors (copyright 2024 jc); TensorTrace structures original results and derives scoped ranks.
license_url
https://creativecommons.org/licenses/by/4.0/
metric_kind
TruthfulQA · Raw
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
data/organizations/qwen/models/qwen2-72b-instruct/benchmarks.json
archive_kind
llmStats
evidence_url
https://huggingface.co/Qwen/Qwen2-72B
git_revision
872b75f63b8d853c46ed17856424029a0c47b1d2
published_at
2025-10-24T17:47:59Z
snapshot_date
2025-10-24T17:47:59Z
source_revision
6e27aa41f51fa8cb327602349240077d1c7acae9fead8ba2f07db0d549927ddc
publisher_anchor
qwen/qwen2-72b-instruct
metric_population
3
current_catalog_url
https://llm-stats.com/
benchmark_evaluation
true
source model id
qwen2-72b-instruct
Original result ↗

LLM Stats · GitHub archive

0.548

source id
llmStatsArchive
leaderboard name
TruthfulQA · Normalized (reported)
dimension
general
metric
TruthfulQA · Normalized (reported)
rank
2
aggregation scope
status
archived
license
CC-BY-4.0
direction
higherIsBetter
conditions
language
en
benchmark
name
TruthfulQA
language
en
modality
text
verified
false
max_score
1
categories
  • general
  • reasoning
  • legal
  • healthcare
  • finance
created_at
2025-07-19T19:56:11.339268+00:00
paper_link
https://arxiv.org/abs/2109.07958
updated_at
2025-07-19T19:56:11.339268+00:00
description
TruthfulQA is a benchmark to measure whether language models are truthful in generating answers to questions. It comprises 817 questions that span 38 categories, including health, law, finance and politics. The questions are crafted such that some humans would answer falsely due to a false belief or misconception, testing models' ability to avoid generating false answers learned from human texts.
benchmark_id
truthfulqa
multilingual
false
analysis_method
Accuracy
is_self_reported
true
verified_by_llmstats
false
attribution
Jonathan Chavez Tamales and LLM Stats contributors (copyright 2024 jc); TensorTrace structures original results and derives scoped ranks.
license_url
https://creativecommons.org/licenses/by/4.0/
metric_kind
TruthfulQA · Normalized (reported)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
data/organizations/qwen/models/qwen2-72b-instruct/benchmarks.json
archive_kind
llmStats
evidence_url
https://huggingface.co/Qwen/Qwen2-72B
git_revision
872b75f63b8d853c46ed17856424029a0c47b1d2
published_at
2025-10-24T17:47:59Z
snapshot_date
2025-10-24T17:47:59Z
source_revision
6e27aa41f51fa8cb327602349240077d1c7acae9fead8ba2f07db0d549927ddc
publisher_anchor
qwen/qwen2-72b-instruct
metric_population
3
current_catalog_url
https://llm-stats.com/
benchmark_evaluation
true
source model id
qwen2-72b-instruct
Original result ↗

LLM Stats · GitHub archive

0.692

source id
llmStatsArchive
leaderboard name
MultiPL-E · Normalized (reported)
dimension
general
metric
MultiPL-E · Normalized (reported)
rank
3
aggregation scope
status
archived
license
CC-BY-4.0
direction
higherIsBetter
conditions
language
en
benchmark
name
MultiPL-E
language
en
modality
text
verified
false
max_score
1
categories
  • general
  • language
created_at
2025-07-19T19:56:12.311919+00:00
paper_link
https://arxiv.org/abs/2208.08227
updated_at
2025-07-19T19:56:12.311919+00:00
description
MultiPL-E is a scalable and extensible system for translating unit test-driven code generation benchmarks to multiple programming languages. It extends HumanEval and MBPP Python benchmarks to 18 additional programming languages, enabling evaluation of neural code generation models across diverse programming paradigms and language features.
benchmark_id
multipl-e
multilingual
true
analysis_method
Pass@1
is_self_reported
true
verified_by_llmstats
false
attribution
Jonathan Chavez Tamales and LLM Stats contributors (copyright 2024 jc); TensorTrace structures original results and derives scoped ranks.
license_url
https://creativecommons.org/licenses/by/4.0/
metric_kind
MultiPL-E · Normalized (reported)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
data/organizations/qwen/models/qwen2-72b-instruct/benchmarks.json
archive_kind
llmStats
evidence_url
https://huggingface.co/Qwen/Qwen2-72B
git_revision
872b75f63b8d853c46ed17856424029a0c47b1d2
published_at
2025-10-24T17:47:59Z
snapshot_date
2025-10-24T17:47:59Z
source_revision
6e27aa41f51fa8cb327602349240077d1c7acae9fead8ba2f07db0d549927ddc
publisher_anchor
qwen/qwen2-72b-instruct
metric_population
4
current_catalog_url
https://llm-stats.com/
benchmark_evaluation
true
source model id
qwen2-72b-instruct
Original result ↗

LLM Stats · GitHub archive

0.692

source id
llmStatsArchive
leaderboard name
MultiPL-E · Raw
dimension
general
metric
MultiPL-E · Raw
rank
3
aggregation scope
status
archived
license
CC-BY-4.0
direction
higherIsBetter
conditions
language
en
benchmark
name
MultiPL-E
language
en
modality
text
verified
false
max_score
1
categories
  • general
  • language
created_at
2025-07-19T19:56:12.311919+00:00
paper_link
https://arxiv.org/abs/2208.08227
updated_at
2025-07-19T19:56:12.311919+00:00
description
MultiPL-E is a scalable and extensible system for translating unit test-driven code generation benchmarks to multiple programming languages. It extends HumanEval and MBPP Python benchmarks to 18 additional programming languages, enabling evaluation of neural code generation models across diverse programming paradigms and language features.
benchmark_id
multipl-e
multilingual
true
analysis_method
Pass@1
is_self_reported
true
verified_by_llmstats
false
attribution
Jonathan Chavez Tamales and LLM Stats contributors (copyright 2024 jc); TensorTrace structures original results and derives scoped ranks.
license_url
https://creativecommons.org/licenses/by/4.0/
metric_kind
MultiPL-E · Raw
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
data/organizations/qwen/models/qwen2-72b-instruct/benchmarks.json
archive_kind
llmStats
evidence_url
https://huggingface.co/Qwen/Qwen2-72B
git_revision
872b75f63b8d853c46ed17856424029a0c47b1d2
published_at
2025-10-24T17:47:59Z
snapshot_date
2025-10-24T17:47:59Z
source_revision
6e27aa41f51fa8cb327602349240077d1c7acae9fead8ba2f07db0d549927ddc
publisher_anchor
qwen/qwen2-72b-instruct
metric_population
4
current_catalog_url
https://llm-stats.com/
benchmark_evaluation
true
source model id
qwen2-72b-instruct
Original result ↗

Safety assessments

1–1 / 1

Foundation Model Transparency Index 2025 ↗

26 / 100

source id
stanfordFMTI
canonical model id
huggingface/Qwen/Qwen2-72B
taxonomy
transparency
hazard category
transparency
hazard name
Organization transparency
policy area
Alibaba
assessment type
organization-level disclosure
metric
disclosure_score
result label
26 / 100
sample size
100
updated at
2026-11-09T18:08:05.227Z

Original sources

1–6 / 6

Hugging Face · Model repository ↗

GitHub · Catalog ↗

GitHub · Catalog ↗

Hugging Face · Catalog ↗

Hugging Face · Catalog ↗

Hugging Face · Catalog ↗

Source links

1–5 / 5

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace