Alibaba · model passport

Qwen: Qwen3 Max Thinking

qwen3-max-thinking

262,144 context

Best percentile: 83.3IFBench (Artificial Analysis)
Composite standing: 62.4shrunk · 3/27 axes

What the data says

Benchmarked on 3 of 27 tracked axes. Every figure below is the model's own published result on that board.

Uneven: 23.4 percentile points between its best and worst axis — 83.3 pct on IFBench (Artificial Analysis) versus 59.9 pct on LiveCodeBench (Artificial Analysis).

IFBench (Artificial Analysis)83.3 pct70.7%Verify →
MMLU-Pro (Artificial Analysis)80.9 pct82.4%Verify →
LiveCodeBench (Artificial Analysis)59.9 pct53.5%Verify →
OverallNot benchmarked
WebDev ArenaNot benchmarked
Vision ArenaNot benchmarked
Factuality ArenaNot benchmarked
Search ArenaNot benchmarked
Document ArenaNot benchmarked
Agent ArenaNot benchmarked
GPQA DiamondNot benchmarked
AIME (math)Not benchmarked
FrontierMathNot benchmarked
SimpleQA VerifiedNot benchmarked
ARC-AGI-2Not benchmarked
Humanity's Last ExamNot benchmarked
SimpleBenchNot benchmarked
LiveBenchNot benchmarked
BFCL v4 (function calling)Not benchmarked
SWE-bench Verified (live board)Not benchmarked
Terminal-Bench 4.0Not benchmarked
HHEM Hallucination (Vectara)Not benchmarked
SWE-bench VerifiedNot benchmarked
Terminal-BenchNot benchmarked
CodingNot benchmarked
Instruction followingNot benchmarked
Hard promptsNot benchmarked

Percentiles are the model's standing within each board's own population. Axes marked "not benchmarked" have no published result for this model — that is an absence of data, not a low score.

How to run it

Use it hosted

API model IDqwen/qwen3-max-thinking

Context length262,144 tokens

Max output65,536 tokens

Input price$0.78 per 1M tokens

Output price$3.90 per 1M tokens

API parameters this endpoint supports

Frequency penaltyInclude reasoningLogprobsMax tokensPresence penaltyReasoningResponse formatSeedStop sequencesStructured outputsTemperatureTool choiceTool callingTop-kTop logprobsTop-p

Example request

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen/qwen3-max-thinking","messages":[{"role":"user","content":"Hello"}]}'

View on OpenRouter →

Identifiers, limits and prices are synced from the upstream source shown above. Any field we haven't synced is left out entirely rather than guessed.

Qwen3 Max Thinking (Preview) stands at 62.4 (raw mean 74.7) — measured on 3 of 27 axes.
standingtemplateVerify →

Every claim is a computed fact from the current board data, phrased by a low-temperature model call and rejected by a validation gate if any number is not in the source row. How the leaderboards work →