Models / qwen3-4b-thinking-2507
Alibabaqwen3-4b-thinking-2507
10 published results from 2 sources. Each card shows where the number comes from and what it does not measure. The overall leaderboard combines them; here each stands alone.
- Provider
- Alibaba
- Sources
- 2
- Our benchmarks
- 0
- Price per million tokens
- Not listed on OpenRouter
Reported by others
8.80
Artificial Analysis Intelligence Index · rank 284 of 314
- Unit
- index score, higher is better
- Configuration
- qwen3-4b-thinking-2507
- Measured
- 1 Oct 2026
- Not shown
- Not business work, and a blend: read the parts for any one task.
66.7%
GPQA Diamond · rank 228 of 276
- Unit
- % of questions, higher is better
- Configuration
- qwen3-4b-thinking-2507
- Measured
- 1 Oct 2026
- Not shown
- Not applied work; multiple-choice science questions.
6.2%
Humanity's Last Exam · rank 270 of 314
- Unit
- % of questions, higher is better
- Configuration
- qwen3-4b-thinking-2507
- Measured
- 1 Oct 2026
- Not shown
- Not everyday work; academic questions at the edge of expertise.
49.8%
IFBench · rank 118 of 215
- Unit
- % of instructions, higher is better
- Configuration
- qwen3-4b-thinking-2507
- Measured
- 1 Oct 2026
- Not shown
- Not judgement about what an instruction meant.
37.3%
Long-context reasoning (AA-LCR) · rank 260 of 309
- Unit
- % of questions, higher is better
- Configuration
- qwen3-4b-thinking-2507
- Measured
- 1 Oct 2026
- Not shown
- Not retrieval over your own document store.
1.5%
Terminal-Bench Hard · rank 206 of 213
- Unit
- % of tasks, higher is better
- Configuration
- qwen3-4b-thinking-2507
- Measured
- 1 Oct 2026
- Not shown
- Not other harnesses; Artificial Analysis no longer runs it on new models.
25.4%
Τ²-bench telecom · rank 189 of 214
- Unit
- % of tasks, higher is better
- Configuration
- qwen3-4b-thinking-2507
- Measured
- 1 Oct 2026
- Not shown
- Not your policies or systems; no longer run on new models.
64.0%
Requested-length error · rank 326 of 370
- Unit
- % off the requested word count, lower is better
- Configuration
- qwen3-4b-thinking-2507
- Measured
- 18 Oct 2025
- Not shown
- Not other format limits such as character counts or bullet counts.
0.28
Style adherence · rank 360 of 370
- Unit
- score from 0 to 1, higher is better
- Configuration
- qwen3-4b-thinking-2507
- Measured
- 18 Oct 2025
- Not shown
- Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
10.9
Writing score · rank 363 of 370
- Unit
- score out of 100, higher is better
- Configuration
- qwen3-4b-thinking-2507
- Measured
- 18 Oct 2025
- Not shown
- Not business copy quality: UGI's prompts are private and lean towards creative writing, and models that often refuse get no score.
Compare qwen3-4b-thinking-2507 with
