Qwen: Qwen3 Next 80B A3B Thinking

Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code …

qwen/qwen3-next-80b-a3b-thinking-2509

Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic...

Specifications & capabilities

Input
text
Output
text
Context window · tokens
262144
Knowledge cutoff
2025-04
Published model ID
Qwen3-Next-80B-A3B-Thinking
Capabilities
reasoning, structuredOutputs, toolCalling

Evaluations

1–14 / 14

OpenCompass LLM

89%

source id
openCompass
leaderboard name
AIME2025
dimension
general
metric
AIME2025
rank
17
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
OverallTable
catalog
open
snapshot
month
REALTIME
fileName
assets/research-rank/research-data.REALTIME.20260309.json
updateTime
2026-03-09
columnFileName
assets/research-rank/research-column.REALTIME.20260309.json
metric_kind
AIME2025
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
0-data.json
source_revision
117c5effa3066abf39f3e8f61109707b09f0cd95223246c07acd6289f4f7fcd2
metric_population
48
benchmark_evaluation
true
source model id
Qwen3-Next-80B-A3B-Thinking
Original result ↗

OpenCompass LLM

69.5%

source id
openCompass
leaderboard name
Average
dimension
general
metric
Average
rank
21
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
OverallTable
catalog
open
snapshot
month
REALTIME
fileName
assets/research-rank/research-data.REALTIME.20260309.json
updateTime
2026-03-09
columnFileName
assets/research-rank/research-column.REALTIME.20260309.json
metric_kind
Average
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
0-data.json
source_revision
117c5effa3066abf39f3e8f61109707b09f0cd95223246c07acd6289f4f7fcd2
metric_population
48
benchmark_evaluation
true
source model id
Qwen3-Next-80B-A3B-Thinking
Original result ↗

HELM Capabilities

46.683%

source id
helm
leaderboard name
HELM Omni-MATH
dimension
intelligence
metric
omni_math_accuracy
rank
22
sample size
1000
source model id
qwen/qwen3-next-80b-a3b-thinking
Original result ↗

OpenCompass LLM

89.5%

source id
openCompass
leaderboard name
IFEval
dimension
general
metric
IFEval
rank
23
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
OverallTable
catalog
open
snapshot
month
REALTIME
fileName
assets/research-rank/research-data.REALTIME.20260309.json
updateTime
2026-03-09
columnFileName
assets/research-rank/research-column.REALTIME.20260309.json
metric_kind
IFEval
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
0-data.json
source_revision
117c5effa3066abf39f3e8f61109707b09f0cd95223246c07acd6289f4f7fcd2
metric_population
48
benchmark_evaluation
true
source model id
Qwen3-Next-80B-A3B-Thinking
Original result ↗

HELM Capabilities

78.6%

source id
helm
leaderboard name
HELM MMLU-Pro
dimension
intelligence
metric
chain_of_thought_correctness
rank
23
sample size
1000
source model id
qwen/qwen3-next-80b-a3b-thinking
Original result ↗

HELM Capabilities

63.004%

source id
helm
leaderboard name
HELM GPQA
dimension
intelligence
metric
chain_of_thought_correctness
rank
23
sample size
446
source model id
qwen/qwen3-next-80b-a3b-thinking
Original result ↗

OpenCompass LLM

82%

source id
openCompass
leaderboard name
MMLU-Pro
dimension
general
metric
MMLU-Pro
rank
24
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
OverallTable
catalog
open
snapshot
month
REALTIME
fileName
assets/research-rank/research-data.REALTIME.20260309.json
updateTime
2026-03-09
columnFileName
assets/research-rank/research-column.REALTIME.20260309.json
metric_kind
MMLU-Pro
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
0-data.json
source_revision
117c5effa3066abf39f3e8f61109707b09f0cd95223246c07acd6289f4f7fcd2
metric_population
48
benchmark_evaluation
true
source model id
Qwen3-Next-80B-A3B-Thinking
Original result ↗

OpenCompass LLM

13.5%

source id
openCompass
leaderboard name
HLE
dimension
general
metric
HLE
rank
24
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
OverallTable
catalog
open
snapshot
month
REALTIME
fileName
assets/research-rank/research-data.REALTIME.20260309.json
updateTime
2026-03-09
columnFileName
assets/research-rank/research-column.REALTIME.20260309.json
metric_kind
HLE
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
0-data.json
source_revision
117c5effa3066abf39f3e8f61109707b09f0cd95223246c07acd6289f4f7fcd2
metric_population
48
benchmark_evaluation
true
source model id
Qwen3-Next-80B-A3B-Thinking
Original result ↗

OpenCompass LLM

66.3%

source id
openCompass
leaderboard name
LiveCodeBenchV6
dimension
general
metric
LiveCodeBenchV6
rank
25
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
OverallTable
catalog
open
snapshot
month
REALTIME
fileName
assets/research-rank/research-data.REALTIME.20260309.json
updateTime
2026-03-09
columnFileName
assets/research-rank/research-column.REALTIME.20260309.json
metric_kind
LiveCodeBenchV6
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
0-data.json
source_revision
117c5effa3066abf39f3e8f61109707b09f0cd95223246c07acd6289f4f7fcd2
metric_population
48
benchmark_evaluation
true
source model id
Qwen3-Next-80B-A3B-Thinking
Original result ↗

OpenCompass LLM

77%

source id
openCompass
leaderboard name
GPQA-Diamond
dimension
general
metric
GPQA-Diamond
rank
26
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
OverallTable
catalog
open
snapshot
month
REALTIME
fileName
assets/research-rank/research-data.REALTIME.20260309.json
updateTime
2026-03-09
columnFileName
assets/research-rank/research-column.REALTIME.20260309.json
metric_kind
GPQA-Diamond
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
0-data.json
source_revision
117c5effa3066abf39f3e8f61109707b09f0cd95223246c07acd6289f4f7fcd2
metric_population
48
benchmark_evaluation
true
source model id
Qwen3-Next-80B-A3B-Thinking
Original result ↗

HELM Capabilities

80.737%

source id
helm
leaderboard name
HELM WildBench
dimension
agentic
metric
wildbench_score_rescaled
rank
29
sample size
1000
source model id
qwen/qwen3-next-80b-a3b-thinking
Original result ↗

HELM Capabilities

80.961%

source id
helm
leaderboard name
HELM IFEval
dimension
agentic
metric
ifeval_strict_accuracy
rank
45
sample size
541
source model id
qwen/qwen3-next-80b-a3b-thinking
Original result ↗

Published prices

1–4 / 4

alibaba/qwen3-next-80b-a3b-thinking ↗

$0.15

Inference provider
vercelAIGatewayCatalog
Platform
Vercel AI Gateway
Unit
input_tokens_per_million
Currency
USD
Billing conditions
model_type
language
quote_scope
gateway_catalog
billing_scope
Vercel public catalog; endpoint prices may differ
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

alibaba/qwen3-next-80b-a3b-thinking ↗

$1.20

Inference provider
vercelAIGatewayCatalog
Platform
Vercel AI Gateway
Unit
output_tokens_per_million
Currency
USD
Billing conditions
model_type
language
quote_scope
gateway_catalog
billing_scope
Vercel public catalog; endpoint prices may differ
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

alibaba/qwen3-next-80b-a3b-thinking ↗

$0.15

Inference provider
vercelAIGatewayCatalog
Platform
vertex
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
vertex | alibaba/qwen3-next-80b-a3b-thinking
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

alibaba/qwen3-next-80b-a3b-thinking ↗

$1.20

Inference provider
vercelAIGatewayCatalog
Platform
vertex
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
vertex | alibaba/qwen3-next-80b-a3b-thinking
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

Provider specifications & access

1–7 / 7

Qwen3 Next 80B A3B Thinking ↗

source model id
alibaba/qwen3-next-80b-a3b-thinking
hosting
vercel-gateway
platforms
  • Vercel AI Gateway
context length
262144
max output tokens
262144
architecture
input_modalities
  • text
output_modalities
  • text
capabilities
  • reasoning
  • structuredOutputs
  • toolCalling

Qwen/Qwen3-Next-80B-A3B-Thinking ↗

source model id
HuggingFace/qwen-qwen3-next-80b-a3b-thinking@1
hosting
foundry-managed-compute
platforms
  • Microsoft Foundry
license
apache-2.0
architecture
input_modalities
  • text
output_modalities
  • text
capabilities

    Qwen/Qwen3-Next-80B-A3B-Thinking ↗

    source model id
    HuggingFace/qwen-qwen3-next-80b-a3b-thinking@2
    hosting
    foundry-managed-compute
    platforms
    • Microsoft Foundry
    license
    apache-2.0
    architecture
    input_modalities
    • text
    output_modalities
    • text
    capabilities

      Qwen/Qwen3-Next-80B-A3B-Thinking ↗

      source model id
      HuggingFace/qwen-qwen3-next-80b-a3b-thinking@3
      hosting
      foundry-managed-compute
      platforms
      • Microsoft Foundry
      license
      apache-2.0
      architecture
      input_modalities
      • text
      output_modalities
      • text
      capabilities

        Qwen/Qwen3-Next-80B-A3B-Thinking ↗

        source model id
        publishers/hf-qwen/models/qwen3-next-80b-a3b-thinking@001
        hosting
        vertex-self-deployed
        platforms
        • Google Cloud Vertex AI
        architecture
        input_modalities
        • text
        output_modalities
        • text
        capabilities

          Qwen3-Next-80B-A3B-Thinking ↗

          source model id
          publishers/qwen/models/qwen3-next@qwen3-next-80b-a3b-thinking
          hosting
          vertex-self-deployed
          platforms
          • Google Cloud Vertex AI
          architecture
          input_modalities
          • text
          output_modalities
          • text
          capabilities

            Qwen3-Next-80B-A3B-Thinking ↗

            source model id
            Qwen/Qwen3-Next-80B-A3B-Thinking
            hosting
            siliconflow-hosted
            platforms
            • SiliconFlow
            max output tokens
            262144
            architecture
            input_modalities
            • text
            output_modalities
            • text
            capabilities
            • toolCalling

            Safety assessments

            1–1 / 1

            Foundation Model Transparency Index 2025 ↗

            26 / 100

            source id
            stanfordFMTI
            canonical model id
            qwen/qwen3-next-80b-a3b-thinking-2509
            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

            Source specification observations

            1–5 / 5

            siliconFlow ↗

            field
            context_length
            value
            262K
            scope
            source-model
            source id
            siliconFlow
            confidence
            1

            vercelAIGatewayCatalog ↗

            field
            context_length
            value
            262144
            normalized value
            262144
            scope
            source-model
            source id
            vercelAIGatewayCatalog
            confidence
            1

            vercelAIGatewayCatalog ↗

            field
            knowledge_cutoff
            reported field
            knowledge_cutoff
            value
            2025-04
            normalized value
            2025-04
            precision
            month
            scope
            source-model
            source id
            vercelAIGatewayCatalog
            confidence
            1

            siliconFlow ↗

            field
            max_output_tokens
            value
            262K
            scope
            source-model
            source id
            siliconFlow
            confidence
            1

            vercelAIGatewayCatalog ↗

            field
            max_output_tokens
            value
            262144
            normalized value
            262144
            scope
            source-model
            source id
            vercelAIGatewayCatalog
            confidence
            1

            Original sources

            1–19 / 19

            SiliconFlow · Model page ↗

            Hugging Face · Model repository ↗

            Google Cloud · Model page ↗

            Google Cloud · Model page ↗

            Microsoft Foundry · Model page ↗

            Microsoft Foundry · Model page ↗

            Microsoft Foundry · Model page ↗

            SiliconFlow · Playground ↗

            Vercel AI Gateway · Model page ↗

            Microsoft Foundry · Model documentation ↗

            SiliconFlow · API documentation ↗

            GitHub · Catalog ↗

            GitHub · Catalog ↗

            Google Cloud · Catalog ↗

            Hugging Face · Catalog ↗

            Microsoft Foundry · Catalog ↗

            SiliconFlow · Catalog ↗

            Vercel AI Gateway · Catalog ↗

            crfm.stanford.edu · 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