Qwen3.7 Max: benchmark scores, price and ranking

Qwen3.7 Max from Alibaba ranks #71 of 743 LLMs on the LLMs Tiger aggregate benchmark score (52.3), based on 26 benchmark results captured up to 2026-10-13.

Organisation

Alibaba

Type

Frontier model

Open weights

No

Released

2026-05-19 (source: epoch)

Cheapest API price

$1.25 in / $3.75 out per million tokens (via novita, observed 2026-10-13T19:47Z)

Aggregate rank

#71 of 743 (score 52.3)

Relative to other models, Qwen3.7 Max is strongest on Epoch ECI (#3 of 204) and weakest on EBR-Bench (#19 of 21).

Across the 25 benchmarks where at least ten models are scored, Qwen3.7 Max is in the top 10% on 3 and in the top half on 20.

Its cheapest listed input price, $1.25 per million tokens, is lower than that of 26% of the 427 models with a listed price.

Qwen3.7 Max benchmark results

About Qwen3.7 Max

Qwen3.7 Max is a frontier model from Alibaba. It was released on 2026-05-19, according to Epoch AI. The cheapest API listing we track charges $1.25 per million input tokens and $3.75 per million output tokens, through novita. We hold 26 benchmark results for it across 4 areas, and 3 are in the top tenth of their boards.

Where Qwen3.7 Max stands

On our aggregate score, Qwen3.7 Max is #71 of 743 ranked models, in the top quarter. Its score is 52.3; the scale is centred on 50, so it sits 2.3 points above the typical model. That beats 90% of the ranked field. Among the 74 ranked Alibaba models it is #3. The next one up is Qwen3.8 Max (xhigh) at 53.2. The next one down is ollama/qwen2.5-coder:32b at 51.9.

Qwen3.7 Max, benchmark by benchmark

On Epoch ECI, Qwen3.7 Max scores 154 and ranks #3 of 204. Only 2 models score higher, led by Qwen 3.8 Max at 156, which is 3 points ahead. It covers Epoch Capabilities Index: Epoch's own aggregate of ~40 benchmarks. The board median is 127, so Qwen3.7 Max is 26 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

On SWE-bench Verified, Qwen3.7 Max scores 77.3% and ranks #3 of 73. Only 2 models score higher, led by Claude Opus 4.7 (max) at 83.5%, which is 6.2 points ahead. It covers real GitHub issues resolved. The board median is 56.4%, so Qwen3.7 Max is 20.9 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

On SimpleBench, Qwen3.7 Max scores 70.4% and ranks #3 of 61. Only 2 models score higher, led by Claude Fable 5 (max) at 81.9%, which is 11.5 points ahead. It covers trick questions that test common sense. The board median is 41.4%, so Qwen3.7 Max is 29.0 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

GPQA Diamond puts Qwen3.7 Max at 90.9%, #29 of 275. That beats 89% of the models tested, but 4.9 points short of GPT-6 Astra (max) (95.8%). The results either side are MiniMax-M3 (90.9%) and Darwin-398B-JGOS (90.9%). It covers expert-level science questions. The board median is 71.7%, so Qwen3.7 Max is 19.2 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

On DTBench, Qwen3.7 Max reaches 92.3%. It ranks #16 of 146, ahead of 89% of the field, and 6.7 points behind Claude Opus 5.5 (max) at 98.9%. The results either side are Claude Sonnet 5 (max) (92.5%) and Qwen3.8 Max (xhigh) (92.0%). It covers dynamic tool-use benchmark. The board median is 68.8%, so Qwen3.7 Max is 23.5 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Qwen3.7 Max manages 95.6% on OTIS Mock AIME, good for #27 of 189. Claude Fable 5.1 (max) leads at 100.0%, 4.4 points further up, and 86% of models sit below. The results either side are Kimi K2.7 Code (95.6%) and GPT-5.4 (xhigh) (95.3%). It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so Qwen3.7 Max is 37.8 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Qwen3.7 Max lands below the middle on LiveBench Mathematics: 85.2%, #10 of 17, with 53% of the field scoring higher. GPT-5.5 (xhigh) leads at 95.9%; the closest result above is gemini-3.5-flash-high at 88.2%. It covers LiveBench release 2026_06_25. The board median is 88.2%, so Qwen3.7 Max is 3.0 points below it. Source: LiveBench 2026_06_25 official CSV, captured 2026-10-13.

Qwen3.7 Max lands below the middle on LiveBench Coding: 74.2%, #11 of 17, with 59% of the field scoring higher. GPT-5.2 Codex leads at 83.6%; the closest result above is gpt-5.2-2025-12-11-high at 76.1%. It covers LiveBench release 2026_06_25. The board median is 76.5%, so Qwen3.7 Max is 2.2 points below it. Source: LiveBench 2026_06_25 official CSV, captured 2026-10-13.

Qwen3.7 Max lands below the middle on LiveBench Agentic Coding: 43.6%, #12 of 17, with 65% of the field scoring higher. claude-opus-4-8-xhigh-effort leads at 56.1%; the closest result above is gemini-3.1-pro-preview-high at 45.4%. It covers LiveBench release 2026_06_25. The board median is 45.8%, so Qwen3.7 Max is 2.2 points below it. Source: LiveBench 2026_06_25 official CSV, captured 2026-10-13.

EBR-Bench is a weak spot. Qwen3.7 Max scores 9.5%, #19 of 21, behind 86% of the models measured. The leader, GPT-6 Astra (max), reaches 76.2%. It covers evidence-based reasoning. The board median is 31.4%, so Qwen3.7 Max is 21.9 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

The full table above also lists the other 16 results, including boards with fewer than ten models, where a rank says little.

Strengths and weaknesses

Software engineering: solid, ahead of 62% of the field on average across 6 benchmarks. Its best board here is SWE-bench Verified (#3 of 73) and its weakest is LiveBench Agentic Coding (#12 of 17). Reasoning, maths and science: solid, ahead of 69% of the field on average across 9 benchmarks. Its best board here is SimpleBench (#3 of 61) and its weakest is LiveBench Mathematics (#10 of 17). General knowledge and chat: solid, ahead of 63% of the field on average across 9 benchmarks. Its best board here is Epoch ECI (#3 of 204) and its weakest is EBR-Bench (#19 of 21).

Price and value

The median input price across the 427 priced models is $0.500 per million tokens, so Qwen3.7 Max costs more than the typical listing. Models that score within 1.5 points or better and cost less: GLM-5.2 (high) ($0.060, 51.6), DeepSeek V4 Flash 0731 (max) ($0.070, 53.1), Qwen3-Coder-30B-A3B-Instruct ($0.070, 52.7). Similar scores cost more on glm-5p1 ($1.40) and gemini-3.5-flash-high ($1.50).

Release history

The Alibaba model released before it was qwen3.7-max-20260517 on 2026-05-17, which scores 47.2. The next one was Qwen3.7 Plus on 2026-06-02, at 48.6.

Reading these numbers

The 26 scores on this page come from 2 sources: Epoch AI Benchmarking Hub (19), LiveBench 2026_06_25 official CSV (7). 7 of them come from an official leaderboard and 19 from datasets or third-party runs. The leaderboard also lists 1 other reasoning-effort setting of this model, which redirect here. This page shows the highest.

Qwen3.7 Max is also listed at 1 other reasoning-effort setting; this page shows the highest-effort row, which is the one the leaderboard keeps by default.

Models ranked nearby

• #68 Gemini 3 Deep Think (2/26) (52.4)
• #69 AI co-mathematician (52.3)
• #70 Darwin-180B-RSI (52.3)
• #72 Intern-S2-Preview (52.3)
• #73 Darwin-397B-ZTC (52.2)
• #74 gemini-3.5-flash-high (52.2)

More from Alibaba

• Qwen 3.6 Max (Preview) (#25, 54.1)
• Qwen3.8 Max (xhigh) (#37, 53.2)
• ollama/qwen2.5-coder:32b (#93, 51.9)
• Qwen3 235B A22B diff, no think, Alibaba API (#122, 51.5)
• Qwen2.5-Coder-14B-Instruct (#135, 51.3)
• Qwen3.5 397B-A17B (#146, 51.1)

Compare it on the live leaderboard → · How the aggregate score works