Qwen3.7 Flash
AlibabaProprietaryReasoningProvisionalReleased Jul 27, 2026Input: text, image, video
Overall score
47.0
Rank 114 of 222 · 32.6–61.3
Context window
1M
1,000,000 tokens
Price per 1M tokens
$0.030 in · $0.13 out
Source: BenchLM
Blended price
$0.055
3:1 input:output tokens
Output speed
—
Not measured yet
Category scores
Scores per capability area with the model's rank among ranked models in that category.
- 1Math37.2
Benchmark results (1)
As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.
Math
| FrontierMath v2 (Tiers 1-3) | 19.298 | #59 of 64 |
Pricing by source
USD per 1M tokens.
| Source | Input | Output | Cached in |
|---|---|---|---|
| List price (BenchLM) | $0.030 | $0.13 | — |
| OpenRouter qwen/qwen3.7-flash | $0.030 | $0.13 | $0.006 |
QwenCloud's official pricing page lists qwen3.7-flash at $0.03 input / $0.13 output per million tokens for requests up to 32K tokens, $0.10 / $0.40 above 32K through 256K, and $0.20 / $0.80 above 256K through 1M. BenchLM stores the lowest tier as the headline API rate and records the higher tiers here.
Speed
Measured by us through OpenRouter (median of trials).
Not measured yet.
Related models
Same family
- Qwen3.7 Max62.6
- Qwen3.7 Plus53.8
- Qwen3.5 Flash42.8
Similar score
- Gemini 3.1 Flash-Lite47.0 · $0.56
- GPT-5.4 nano46.9 · $0.46
- Ling 3.0 Flash VL46.8 · $0.090
- Nemotron 3 Ultra46.8 · $1.05
- GPT-5 (medium)46.0 · —