AI models
Qwen3.8 27B vs Gemma 4 31B
Same criteria, side by side. Where the gap is small, it may be measurement noise.
Also searched as
Qwen3.8 vs Gemma
Direct answer: GPQA Diamond (OpenRouter): Qwen3.8 27B 87.2%, Gemma 4 31B 85.9% (OpenRouter Benchmarks). τ-bench Verified (airline): Qwen3.8 27B 78%, Gemma 4 31B 77% (OpenRouter Benchmarks).
| Metric | Qwen3.8 27B | Gemma 4 31B | Source |
|---|---|---|---|
| Weights ?what it is | open | open | no data |
| Input US$/1M ? | US$ 0.15 | US$ 0.20 | no data |
| Output US$/1M ? | US$ 1.88 | US$ 0.40 | no data |
| Context ? | 1,048,575 | 262,144 | no data |
| GPQA Diamond ? | no data | 75.8% | Epoch AI |
| OTIS Mock AIME ? | no data | 73.3% | Epoch AI |
| SimpleQA Verified ? | no data | 10.4% | Epoch AI |
| GPQA Diamond (OpenRouter) ? | 87.2% | 85.9% | OpenRouter Benchmarks |
| τ-bench Verified (airline) ? | 78% | 77% | OpenRouter Benchmarks |
Compare with
Sources
- Epoch AI, CC BY 4.0, latest version we checked.
- OpenRouter Benchmarks, CC BY 4.0, latest version we checked.
- OpenRouter, dados públicos da API; exports de benchmarks e rankings em CC BY 4.0, latest version we checked.
Dates come from the sources: OpenRouter listing or Hugging Face repo creation, which may differ from the official launch. Family and version were grouped by rule from the name.