DeepSeek: DeepSeek V3.1 Terminus

DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language con…

deepseek/deepseek-v3.1-terminus

DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's performance in coding and search agents. It is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)

The model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows.

Specifications & capabilities

Input
text
Output
text
Context window · tokens
163840
Knowledge cutoff
2025-03-31
Published model ID
DeepSeek-V3.1-Terminus
Capabilities
reasoning, structuredOutputs, toolCalling
Description source ↗

Evaluations

1–20 / 54

OpenRouter Benchmarks

73.333%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Novita
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
21
sample size
100
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
2
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
tau_bench_verified_airline
name
tau2-bench Verified Airline
record_kind
aggregate
provider_name
Novita
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-08-29T16:33:37.924Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
tau2-bench Verified Airline · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
100
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.7333335
accuracy_std_dev
0.026666499999999982
cost_per_task_usd
0.06130771
output_tokens_per_task
14346.49
latency_seconds_per_task
487.79715000000004
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
52
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v3.1-terminus
source model id
deepseek/deepseek-v3.1-terminus
Original result ↗

OpenRouter Benchmarks

79.966%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · AtlasCloud
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
23
sample size
396
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
2
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
AtlasCloud
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-08-29T19:12:57.906Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
396
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.7996630000000001
accuracy_std_dev
0.006734000000000018
cost_per_task_usd
0.01377076515151515
output_tokens_per_task
14276.108585858587
latency_seconds_per_task
290.6563838383838
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
30
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v3.1-terminus
source model id
deepseek/deepseek-v3.1-terminus
Original result ↗

OpenRouter Benchmarks

79.545%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · StreamLake
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
25
sample size
396
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
2
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
StreamLake
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-08-29T16:10:33.070Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
396
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.7954545
accuracy_std_dev
0.010942500000000022
cost_per_task_usd
0.014605156565656566
output_tokens_per_task
13980.005050505051
latency_seconds_per_task
301.5307196969697
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
30
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v3.1-terminus
source model id
deepseek/deepseek-v3.1-terminus
Original result ↗

OpenRouter Benchmarks

46.667%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · SiliconFlow
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
25
sample size
100
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
2
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
tau_bench_verified_airline
name
tau2-bench Verified Airline
record_kind
aggregate
provider_name
SiliconFlow
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-08-29T16:26:59.974Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
tau2-bench Verified Airline · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
100
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.466667
accuracy_std_dev
0
cost_per_task_usd
0.06821334999999999
output_tokens_per_task
4113.59
latency_seconds_per_task
285.66619000000003
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
28
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v3.1-terminus
source model id
deepseek/deepseek-v3.1-terminus
Original result ↗

OpenRouter Benchmarks

8.667%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · AtlasCloud
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
29
sample size
100
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
2
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
tau_bench_verified_airline
name
tau2-bench Verified Airline
record_kind
aggregate
provider_name
AtlasCloud
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-08-29T16:17:08.780Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
tau2-bench Verified Airline · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
100
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.08666650000000001
accuracy_std_dev
0.013333500000000005
cost_per_task_usd
0.00166133
output_tokens_per_task
202.06
latency_seconds_per_task
9.31
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
29
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v3.1-terminus
source model id
deepseek/deepseek-v3.1-terminus
Original result ↗

OpenRouter Benchmarks

82.66%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Novita
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
30
sample size
396
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
2
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Novita
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-08-29T18:35:57.732Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
396
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8265989999999999
accuracy_std_dev
0
cost_per_task_usd
0.01892201515151515
output_tokens_per_task
18768.85606060606
latency_seconds_per_task
495.658101010101
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
59
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v3.1-terminus
source model id
deepseek/deepseek-v3.1-terminus
Original result ↗

OpenRouter Benchmarks

0.337%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · SiliconFlow
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
33
sample size
198
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
1
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
SiliconFlow
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-08-22T17:29:06.480Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
198
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.0033670000000000006
cost_per_task_usd
0.0034259191919191923
output_tokens_per_task
3225.4444444444443
latency_seconds_per_task
169.43220707070708
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
34
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v3.1-terminus
source model id
deepseek/deepseek-v3.1-terminus
Original result ↗

OpenRouter Benchmarks

73%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · auto-routing
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
51
sample size
100
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
2
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
tau_bench_verified_airline
name
tau2-bench Verified Airline
record_kind
aggregate
provider_name
auto-routing
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-08-29T16:22:37.842Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
tau2-bench Verified Airline · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
100
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.73
accuracy_std_dev
0.0033330000000000304
cost_per_task_usd
0.06290177
output_tokens_per_task
14483.09
latency_seconds_per_task
485.84577
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
128
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v3.1-terminus
source model id
deepseek/deepseek-v3.1-terminus
Original result ↗

LMArena

1,451.133

source id
lmarena
leaderboard name
LMArena Text Industry Medicine And Healthcare
dimension
general
metric
Arena rating
rank
72
sample size
259
evaluated at
2026-11-09T00:00:00.000Z
source model id
DeepSeek-V3.1-Terminus
confidence lower
1414.032911373161
confidence upper
1488.23235152326
Original result ↗

LMArena

1,451.06

source id
lmarena
leaderboard name
LMArena Text Industry Life And Physical And Social Science
dimension
general
metric
Arena rating
rank
80
sample size
570
evaluated at
2026-11-09T00:00:00.000Z
source model id
DeepSeek-V3.1-Terminus
confidence lower
1426.8456952875836
confidence upper
1475.2742082516265
Original result ↗

OpenRouter Benchmarks

77.189%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · auto-routing
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
88
sample size
396
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
2
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
auto-routing
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-08-29T18:21:38.666Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
396
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.7718855
accuracy_std_dev
0.0025254999999999583
cost_per_task_usd
0.017657098484848484
output_tokens_per_task
17493.924242424244
latency_seconds_per_task
452.1440101010101
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
132
benchmark_evaluation
true
openrouter_permaslug
deepseek/deepseek-v3.1-terminus
source model id
deepseek/deepseek-v3.1-terminus
Original result ↗

LMArena

1,403.605

source id
lmarena
leaderboard name
LMArena Text Creative Writing
dimension
general
metric
Arena rating
rank
92
sample size
446
evaluated at
2026-11-09T00:00:00.000Z
source model id
DeepSeek-V3.1-Terminus
confidence lower
1376.2158384325828
confidence upper
1430.9938458160539
Original result ↗

LMArena

1,423.656

source id
lmarena
leaderboard name
LMArena Text Russian
dimension
general
metric
Arena rating
rank
95
sample size
304
evaluated at
2026-11-09T00:00:00.000Z
source model id
DeepSeek-V3.1-Terminus
confidence lower
1392.875359351914
confidence upper
1454.4360554598966
Original result ↗

LMArena

1,456.558

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Medicine And Healthcare
dimension
style
metric
Arena rating
rank
100
sample size
259
evaluated at
2026-11-09T00:00:00.000Z
source model id
DeepSeek-V3.1-Terminus
confidence lower
1418.776833330537
confidence upper
1494.3384457466184
Original result ↗

LMArena

1,407.218

source id
lmarena
leaderboard name
LMArena Text Industry Writing And Literature And Language
dimension
general
metric
Arena rating
rank
104
sample size
789
evaluated at
2026-11-09T00:00:00.000Z
source model id
DeepSeek-V3.1-Terminus
confidence lower
1386.4975050734033
confidence upper
1427.938927219277
Original result ↗

LMArena

1,404.846

source id
lmarena
leaderboard name
LMArena Text Style Control Creative Writing
dimension
style
metric
Arena rating
rank
105
sample size
446
evaluated at
2026-11-09T00:00:00.000Z
source model id
DeepSeek-V3.1-Terminus
confidence lower
1377.603367127235
confidence upper
1432.0884599793526
Original result ↗

LMArena

1,451.6

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Life And Physical And Social Science
dimension
style
metric
Arena rating
rank
112
sample size
570
evaluated at
2026-11-09T00:00:00.000Z
source model id
DeepSeek-V3.1-Terminus
confidence lower
1427.3191560762798
confidence upper
1475.8802938922197
Original result ↗

LMArena

1,407.804

source id
lmarena
leaderboard name
LMArena Text Non English
dimension
general
metric
Arena rating
rank
113
sample size
2025
evaluated at
2026-11-09T00:00:00.000Z
source model id
DeepSeek-V3.1-Terminus
confidence lower
1394.9083430839632
confidence upper
1420.6999566415843
Original result ↗

LMArena

1,406.763

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Writing And Literature And Language
dimension
style
metric
Arena rating
rank
115
sample size
789
evaluated at
2026-11-09T00:00:00.000Z
source model id
DeepSeek-V3.1-Terminus
confidence lower
1385.9386775173448
confidence upper
1427.5880204788639
Original result ↗

LMArena

1,420.859

source id
lmarena
leaderboard name
LMArena Text Style Control Russian
dimension
style
metric
Arena rating
rank
121
sample size
304
evaluated at
2026-11-09T00:00:00.000Z
source model id
DeepSeek-V3.1-Terminus
confidence lower
1390.194271356698
confidence upper
1451.5243769182741
Original result ↗

Published prices

1–6 / 6

Provider specifications & access

1–3 / 3

DeepSeek-V3.1-Terminus ↗

source model id
deepseek-ai/DeepSeek-V3.1-Terminus
hosting
siliconflow-hosted
platforms
  • SiliconFlow
max output tokens
163840
architecture
input_modalities
  • text
output_modalities
  • text
capabilities
  • reasoning
  • structuredOutputs
  • toolCalling

deepseek-ai/DeepSeek-V3.1-Terminus ↗

source model id
publishers/deepseek-ai/models/deepseek-v3-1@deepseek-v3-1-terminus
hosting
vertex-self-deployed
platforms
  • Google Cloud Vertex AI
architecture
input_modalities
  • text
output_modalities
  • text
capabilities

    deepseek-ai/DeepSeek-V3.1-Terminus ↗

    source model id
    publishers/hf-deepseek-ai/models/deepseek-v3.1-terminus@001
    hosting
    vertex-self-deployed
    platforms
    • Google Cloud Vertex AI
    architecture
    input_modalities
    • text
    output_modalities
    • text
    capabilities

      Safety assessments

      1–1 / 1

      Foundation Model Transparency Index 2025 ↗

      32 / 100

      source id
      stanfordFMTI
      canonical model id
      deepseek/deepseek-v3.1-terminus
      taxonomy
      transparency
      hazard category
      transparency
      hazard name
      Organization transparency
      policy area
      DeepSeek
      assessment type
      organization-level disclosure
      metric
      disclosure_score
      result label
      32 / 100
      sample size
      100
      updated at
      2026-11-09T18:08:05.227Z

      Source specification observations

      1–5 / 5

      openRouter ↗

      field
      context_length
      value
      163840
      normalized value
      163840
      scope
      source-model
      source id
      openRouter
      confidence
      1

      siliconFlow ↗

      field
      context_length
      value
      164K
      scope
      source-model
      source id
      siliconFlow
      confidence
      1

      openRouter ↗

      field
      knowledge_cutoff
      reported field
      knowledge_cutoff
      value
      2025-03-31
      normalized value
      2025-03-31
      precision
      day
      scope
      source-model
      source id
      openRouter
      confidence
      1

      openRouter ↗

      field
      max_output_tokens
      value
      147456
      normalized value
      147456
      scope
      source-model
      source id
      openRouter
      confidence
      1

      siliconFlow ↗

      field
      max_output_tokens
      value
      164K
      scope
      source-model
      source id
      siliconFlow
      confidence
      1

      Original sources

      1–17 / 17

      DeepSeek · Model reference ↗

      SiliconFlow · Model page ↗

      Hugging Face · Model repository ↗

      DeepInfra · Model page ↗

      Google Cloud · Model page ↗

      Google Cloud · Model page ↗

      OpenRouter · Model page ↗

      SiliconFlow · Playground ↗

      SiliconFlow · API documentation ↗

      DeepInfra · Catalog ↗

      Epoch AI · Catalog ↗

      GitHub · Catalog ↗

      Google Cloud · Catalog ↗

      LMArena · Catalog ↗

      OpenRouter · Catalog ↗

      OpenRouter · Catalog ↗

      SiliconFlow · Catalog ↗

      Source links

      1–10 / 10

      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