Qwen3.7 Flash: benchmark scores, price and ranking

Qwen3.7 Flash from Alibaba ranks #189 of 743 LLMs on the LLMs Tiger aggregate benchmark score (50.5), based on 6 benchmark results captured up to 2026-10-13.

Organisation: Alibaba
Type: Fast / low-cost (flash) model
Open weights: No
Released: 2026-07-27 (source: epoch)
Cheapest API price: $0.030 in / $0.130 out per million tokens (via openrouter, observed 2026-10-13T20:47Z)
Aggregate rank: #189 of 743 (score 50.5)

Relative to other models, Qwen3.7 Flash is strongest on Epoch ECI (#29 of 204) and weakest on FrontierMath T1-3 (#56 of 68).

Across the 6 benchmarks where at least ten models are scored, Qwen3.7 Flash is in the top 10% on 0 and in the top half on 4.

Its cheapest listed input price, $0.030 per million tokens, is lower than that of 96% of the 427 models with a listed price.

Qwen3.7 Flash benchmark results

Qwen3.7 Flash benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
Epoch ECI	145	#29 of 204	Epoch AI Benchmarking Hub	2026-10-13
OTIS Mock AIME	86.7%	#56 of 189	Epoch AI Benchmarking Hub	2026-10-13
Chess Puzzles	23.0%	#37 of 122	Epoch AI Benchmarking Hub	2026-10-13
GPQA Diamond	82.3%	#98 of 275	Epoch AI Benchmarking Hub	2026-10-13
Mystery Games	15.0%	#42 of 59	Epoch AI Benchmarking Hub	2026-10-13
FrontierMath T1-3	19.3%	#56 of 68	Epoch AI Benchmarking Hub	2026-10-13

About Qwen3.7 Flash

Qwen3.7 Flash is a smaller, lower-cost model from Alibaba. It was released on 2026-07-27, according to Epoch AI. The cheapest API listing we track charges $0.030 per million input tokens and $0.130 per million output tokens, through openrouter. We hold 6 benchmark results for it across 2 areas, and none is in the top tenth of its board.

Where Qwen3.7 Flash stands

On our aggregate score, Qwen3.7 Flash is #189 of 743 ranked models, around the middle of the table. Its score is 50.5; the scale is centred on 50, so it sits 0.5 points above the typical model. That beats 75% of the ranked field. Among the 74 ranked Alibaba models it is #11. The next one up is qwen-2.5-72b-instruct at 50.7. The next one down is ollama/Qwen2.5.1-Coder-7B-Instruct-GGUF:Q8_0-32k at 50.4.

Qwen3.7 Flash, benchmark by benchmark

Epoch ECI puts Qwen3.7 Flash at 145, #29 of 204. That beats 86% of the models tested, but 12 points short of Qwen 3.8 Max (156). The results either side are Gemini 2.5 Pro (Jun 2025) (145) and grok-4-fast (144). It covers Epoch Capabilities Index: Epoch's own aggregate of ~40 benchmarks. The board median is 127, so Qwen3.7 Flash is 17 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

On OTIS Mock AIME, Qwen3.7 Flash reaches 86.7%. It ranks #56 of 189, ahead of 70% of the field, and 13.3 points behind Claude Fable 5.1 (max) at 100.0%. The results either side are Qwen3.6 35B-A3B (86.7%) and Qwen 3.6 Flash (2026-04-16) (84.4%). It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so Qwen3.7 Flash is 28.9 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Qwen3.7 Flash manages 23.0% on Chess Puzzles, good for #37 of 122. GPT-6 Astra (max) leads at 72.0%, 49.0 points further up, and 70% of models sit below. The results either side are Qwen3.7 Plus (24.0%) and Qwen3.5 Plus (22.0%). It covers chess tactics puzzles. The board median is 12.5%, so Qwen3.7 Flash is 10.5 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

GPQA Diamond puts Qwen3.7 Flash at 82.3%, #98 of 275. That beats 64% of the models tested, but 13.4 points short of GPT-6 Astra (max) (95.8%). The results either side are Qwen3.5 Flash (82.3%) and o3 (high) (81.8%). It covers expert-level science questions. The board median is 71.7%, so Qwen3.7 Flash is 10.6 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Qwen3.7 Flash lands below the middle on Mystery Games: 15.0%, #42 of 59, with 69% of the field scoring higher. GPT-6 Astra (max) leads at 84.0%; the closest result above is Qwen3.7 Plus at 17.0%. It covers deductive reasoning puzzles. The board median is 23.0%, so Qwen3.7 Flash is 8.0 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

FrontierMath T1-3 is a weak spot. Qwen3.7 Flash scores 19.3%, #56 of 68, behind 81% of the models measured. The leader, GPT-6 Astra (max), reaches 93.7%. It covers research-level maths, tiers 1-3. The board median is 55.6%, so Qwen3.7 Flash is 36.3 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Strengths and weaknesses

Reasoning, maths and science: solid, ahead of 51% of the field on average across 3 benchmarks. Its best board here is OTIS Mock AIME (#56 of 189) and its weakest is FrontierMath T1-3 (#56 of 68). General knowledge and chat: solid, ahead of 61% of the field on average across 3 benchmarks. Its best board here is Epoch ECI (#29 of 204) and its weakest is Mystery Games (#42 of 59).

Price and value

The median input price across the 427 priced models is $0.500 per million tokens, so Qwen3.7 Flash 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 Flash 0731 (max) ($0.016, 53.1), GLM-5.3-Flash (max) ($0.026, 49.6). Similar scores cost more on GLM-5.2 (high) ($0.060) and glm-4.7-flash ($0.060).

Release history

The Alibaba model released before it was Qwen3.7 Plus on 2026-06-02, which scores 48.6. The next one was Qwen3.8 Max (xhigh) on 2026-08-02, at 53.2.

Reading these numbers

The 6 scores on this page come from 1 source: Epoch AI Benchmarking Hub (6). No official leaderboard supplied any of them, so treat them as third-party measurements. With 6 results the aggregate rank can move a lot when one new score arrives.

Models ranked nearby

#186 gemini-2.5-flash-preview-05-20 (50.5)
#187 Kimi K2 Thinking Turbo (50.5)
#188 swe-search (50.5)
#190 gemini-2.5-pro_16K (50.4)
#191 nousresearch/hermes-3-llama-3.1-405b (50.4)
#192 ollama/Qwen2.5.1-Coder-7B-Instruct-GGUF:Q8_0-32k (50.4)