LLMs TigerLive LLM benchmarks

Qwen3.7 Plus: benchmark scores, price and ranking

Qwen3.7 Plus from Alibaba ranks #339 of 743 LLMs on the LLMs Tiger aggregate benchmark score (48.6), based on 14 benchmark results captured up to 2026-10-13.

Organisation
Alibaba
Type
Frontier model
Open weights
No
Released
2026-06-02 (source: epoch)
Cheapest API price
$0.282 in / $1.13 out per million tokens (via aihubmix, observed 2026-10-13T19:47Z)
Aggregate rank
#339 of 743 (score 48.6)

Relative to other models, Qwen3.7 Plus is strongest on Epoch ECI (#16 of 204) and weakest on FrontierCode (#13 of 15).

Across the 13 benchmarks where at least ten models are scored, Qwen3.7 Plus is in the top 10% on 1 and in the top half on 9.

Its cheapest listed input price, $0.282 per million tokens, is lower than that of 62% of the 427 models with a listed price.

Qwen3.7 Plus benchmark results

Qwen3.7 Plus benchmark scores, ranked against all models measured on each benchmark
BenchmarkScoreRankSourceCaptured
Epoch ECI147#16 of 204Epoch AI Benchmarking Hub2026-10-13
OTIS Mock AIME93.3%#34 of 189Epoch AI Benchmarking Hub2026-10-13
GPQA Diamond87.9%#52 of 275Epoch AI Benchmarking Hub2026-10-13
DTBench84.0%#40 of 146Epoch AI Benchmarking Hub2026-10-13
Chess Puzzles24.0%#36 of 122Epoch AI Benchmarking Hub2026-10-13
LMCA37.6%#36 of 108Epoch AI Benchmarking Hub2026-10-13
CritPt9.1%#42 of 115Epoch AI Benchmarking Hub2026-10-13
SciCode45.5%#50 of 106Epoch AI Benchmarking Hub2026-10-13
LMArena Document Elo1,444#9 of 18LMArena2026-10-13
Mystery Games17.0%#41 of 59Epoch AI Benchmarking Hub2026-10-13
FrontierMath T1-334.4%#48 of 68Epoch AI Benchmarking Hub2026-10-13
LMArena Vision Elo1,265#16 of 22LMArena2026-10-05
FrontierCode10.2%#13 of 15Epoch AI Benchmarking Hub2026-10-13
OSWorld 22.8%#8 of 8Epoch AI Benchmarking Hub2026-10-13

About Qwen3.7 Plus

Qwen3.7 Plus is a frontier model from Alibaba. It was released on 2026-06-02, according to Epoch AI. The cheapest API listing we track charges $0.282 per million input tokens and $1.13 per million output tokens, through aihubmix. We hold 14 benchmark results for it across 4 areas, and 1 is in the top tenth of its board.

Where Qwen3.7 Plus stands

On our aggregate score, Qwen3.7 Plus is #339 of 743 ranked models, around the middle of the table. Its score is 48.6; the scale is centred on 50, so it sits 1.4 points below the typical model. That beats 54% of the ranked field. Among the 74 ranked Alibaba models it is #33. The next one up is qwen-plus-2025-04-28 at 48.9. The next one down is qwen2.5-coder:7b-instruct-q8_0 at 48.5.

Qwen3.7 Plus, benchmark by benchmark

On Epoch ECI, Qwen3.7 Plus scores 147 and ranks #16 of 204. Only 15 models score higher, led by Qwen 3.8 Max at 156, which is 9 points ahead. It covers Epoch Capabilities Index: Epoch's own aggregate of ~40 benchmarks. The board median is 127, so Qwen3.7 Plus is 20 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

On OTIS Mock AIME, Qwen3.7 Plus reaches 93.3%. It ranks #34 of 189, ahead of 82% of the field, and 6.7 points behind Claude Fable 5.1 (max) at 100.0%. The results either side are Qwen 3.6 Plus (2026-04-02) (93.3%) and grok-4.20-0309-reasoning (92.2%). It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so Qwen3.7 Plus is 35.6 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Qwen3.7 Plus manages 87.9% on GPQA Diamond, good for #52 of 275. GPT-6 Astra (max) leads at 95.8%, 7.9 points further up, and 81% of models sit below. The results either side are Kimi K2.7 Code (87.9%) and GLM-4.7-FP8 (87.9%). It covers expert-level science questions. The board median is 71.7%, so Qwen3.7 Plus is 16.2 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

DTBench puts Qwen3.7 Plus at 84.0%, #40 of 146. That beats 73% of the models tested, but 14.9 points short of Claude Opus 5.5 (max) (98.9%). The results either side are mimo-v2.5-pro (84.5%) and Qwen3.5 Flash (82.9%). It covers dynamic tool-use benchmark. The board median is 68.8%, so Qwen3.7 Plus is 15.2 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

On Chess Puzzles, Qwen3.7 Plus reaches 24.0%. It ranks #36 of 122, ahead of 70% of the field, and 48.0 points behind GPT-6 Astra (max) at 72.0%. The results either side are grok-4.20-0309-reasoning (24.0%) and Qwen3.7 Flash (23.0%). It covers chess tactics puzzles. The board median is 12.5%, so Qwen3.7 Plus is 11.5 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Qwen3.7 Plus manages 37.6% on LMCA, good for #36 of 108. Claude Opus 5.5 (max) leads at 68.2%, 30.7 points further up, and 67% of models sit below. The results either side are Inkling (xhigh) (37.6%) and Claude Opus 4 (37.4%). It covers language-model capability assessment. The board median is 29.2%, so Qwen3.7 Plus is 8.4 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Qwen3.7 Plus lands below the middle on Mystery Games: 17.0%, #41 of 59, with 68% of the field scoring higher. GPT-6 Astra (max) leads at 84.0%; the closest result above is Qwen3.5 Plus at 17.0%. It covers deductive reasoning puzzles. The board median is 23.0%, so Qwen3.7 Plus is 6.0 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Qwen3.7 Plus lands below the middle on FrontierMath T1-3: 34.4%, #48 of 68, with 69% of the field scoring higher. GPT-6 Astra (max) leads at 93.7%; the closest result above is Qwen3.6 27B at 35.1%. It covers research-level maths, tiers 1-3. The board median is 55.6%, so Qwen3.7 Plus is 21.2 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Qwen3.7 Plus lands below the middle on LMArena Vision Elo: 1,265, #16 of 22, with 68% of the field scoring higher. Gemini 3.7 Flash (high) leads at 1,296; the closest result above is Kimi K2.6 at 1,265. It covers crowd-voted image understanding. The board median is 1,279, so Qwen3.7 Plus is 14 points below it. Source: LMArena, captured 2026-10-05.

FrontierCode is a weak spot. Qwen3.7 Plus scores 10.2%, #13 of 15, behind 80% of the models measured. The leader, Claude Opus 5 (max), reaches 53.4%. It covers hard programming tasks. The board median is 31.8%, so Qwen3.7 Plus is 21.6 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

The full table above also lists the other 4 results, including boards with fewer than ten models, where a rank says little.

Strengths and weaknesses

Software engineering: uneven, ahead of 33% of the field on average across 2 benchmarks. Its best board here is SciCode (#50 of 106) and its weakest is FrontierCode (#13 of 15). Reasoning, maths and science: solid, ahead of 64% of the field on average across 4 benchmarks. Its best board here is OTIS Mock AIME (#34 of 189) and its weakest is FrontierMath T1-3 (#48 of 68). General knowledge and chat: solid, ahead of 56% of the field on average across 6 benchmarks. Its best board here is Epoch ECI (#16 of 204) and its weakest is LMArena Vision Elo (#16 of 22).

Price and value

The median input price across the 427 priced models is $0.500 per million tokens, so Qwen3.7 Plus costs less than the typical listing. Models that score within 1.5 points or better and cost less: Qwen2.5-Coder-7B-Instruct ($0.010, 49.5), DeepSeek V4.1 Flash (high) ($0.010, 48.9), Llama-3.2-3B-Instruct ($0.020, 47.2). Similar scores cost more on gemini-2.5-flash-preview-09-2025 ($0.300) and MiniMax-M2.1 ($0.300).

Release history

The Alibaba model released before it was Qwen3.7 Max on 2026-05-19, which scores 52.3. The next one was Qwen3.7 Flash on 2026-07-27, at 50.5.

Reading these numbers

The 14 scores on this page come from 2 sources: Epoch AI Benchmarking Hub (12), LMArena (2). No official leaderboard supplied any of them, so treat them as third-party measurements.

Models ranked nearby

More from Alibaba

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