Up to four models
Qwen3.8-27B vs Mistral Large 4
On the index (GPT-4 = 100), Qwen3.8-27B scores 161 and Mistral Large 4 160. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
Qwen3.8-27B161145–178
WeightsOpen
ReleasedAug 2026
Price in / out$0.039 / $1.25
Context1M
Core tests taken3 of 9
Mistral Large 4160144–177
WeightsOpen
ReleasedOct 2026
Price in / out$1.36 / $4.18
Context1.05M
Core tests taken4 of 9
Qwen3.8-27B and Mistral Large 4 are too close to call (1 point apart, within the uncertainty), ahead on 0 of 1 shared core tests, and costs 6.0× less.
Test by testthird-party results
Qwen3.8-27BMistral Large 4Every result as a table
| Test | Qwen3.8-27B | Mistral Large 4 |
|---|---|---|
| Maths | ||
| ProofBench v1.1 | 16.0% | 10.0% |
| Surface Evolver Bench | 45.0% | 28.1% |
| Coding | ||
| Code Migration | 14.2% | 30.6% |
| IOI | 39.1% | 45.3% |
| Vibe Code Bench v1.1 | 64.8% | 78.4% |
| Agents | ||
| DTBench | 88.0% | 88.2% |
| LMCA | 41.4% | 35.8% |
| Professional work | ||
| Finance Agent (v2) | 48.5% | 54.7% |
| EMB | 59.7% | 56.2% |
| Legal Research Bench | 36.1% | 31.7% |
| MedCode | 28.7% | 40.7% |
| MedScribe | 83.9% | 80.4% |
| Tax Agent Bench | 30.9% | 30.4% |
Tests at least two of these models have taken. Bold rows are the core tests.
