Skip to content
aiqbench

Alibaba · model passport

Qwen: Qwen3.7 Plus

qwen3-7-plus
  • Cloud only
  • Proprietary licence
  • 1,000,000 context
  • Released 2026-09-13(first seen on LMArena)
11/27axes covered
Overall · LMArena
1,456#59 of 395
Best percentile
96.6IFBench (Artificial Analysis)
Cohort standing
66.9median 60.2

What the data says

Benchmarked on 11 of 27 tracked axes. Every figure below is the model's own published result on that board.

Strongest axes

  • 96.6 pct — IFBench (Artificial Analysis) (78.0%)
  • 85.6 pct — Instruction following (1,447)
  • 85.3 pct — Overall (1,456)

Uneven: 78.4 percentile points between its best and worst axis — 96.6 pct on IFBench (Artificial Analysis) versus 18.2 pct on Agent Arena.

  • IFBench (Artificial Analysis)96.6 pct78.0%Verify →
  • Instruction following85.6 pct1,447Verify →
  • Overall85.3 pct1,456Verify →
  • Coding82.8 pct1,500Verify →
  • Hard prompts82.8 pct1,473Verify →
  • Vision Arena77.3 pct1,264Verify →
  • AIME (math)77 pct93.3%Verify →
  • GPQA Diamond75.6 pct87.9%Verify →
  • Factuality Arena69 pct1,453Verify →
  • Document Arena36.8 pct1,453Verify →
  • Agent Arena18.2 pct-0.063Verify →
  • WebDev ArenaNot benchmarked
  • Search ArenaNot 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
  • MMLU-Pro (Artificial Analysis)Not benchmarked
  • LiveCodeBench (Artificial Analysis)Not benchmarked
  • HHEM Hallucination (Vectara)Not benchmarked
  • SWE-bench VerifiedNot benchmarked
  • Terminal-BenchNot 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/qwen3.7-plus
Context length1,000,000 tokens
Max output131,072 tokens
Acceptstext, image
Input price$0.32 per 1M tokens
Cached input price$0.06 per 1M tokens
Output price$1.28 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/qwen3.7-plus","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.

  • The qwen3.7-plus model from alibaba has a shrunk composite score of 66.9 and a raw composite score of 71.5, with coverage on 11 of 27 axes.

    standingVerify →

  • Over the past 180 days, qwen3.7-plus from alibaba has a standing of 66.9, compared with a cohort median standing of 60.2 across 177 models.

    cohortVerify →

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 →