Model comparison
DeepSeek-V3.1-Terminus vs Mistral
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 29.9 on the Noometry Index.
Last verified . 10 shared benchmarks.
DeepSeek
Mistral AISummary
- They share 10 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 7 categories and Mistral in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1-Terminus leads 61.0 to 37.0.
- DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1-Terminus | Mistral | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 43.1 | 29.9 |
| Released | 2025-09-22 | — |
| Weights | Open | Proprietary |
| Context window | 164K | — |
| Max output | 147K | — |
| Input $ / M tokens | $0.27 | — |
| Output $ / M tokens | $1 | — |
| Results tracked | 16 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 42.0 (#113), Mistral: 33.8 (#250)
| Benchmark | DeepSeek-V3.1-Terminus | Mistral |
|---|---|---|
| LMArena Coding | 1426 | 1162 |
| SciCode | 40.6% | — |
| ALE-Bench | 745.17 | — |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 26.4 (#133), Mistral: 22.2 (#200)
| Benchmark | DeepSeek-V3.1-Terminus | Mistral |
|---|---|---|
| LMArena Hard Prompts | 1426 | 1149 |
| Kagi LLM Benchmark | 57.4% | — |
| CritPt | 1.7% | — |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |
Math DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 38.5 (#137), Mistral: 22.3 (#278)
| Benchmark | DeepSeek-V3.1-Terminus | Mistral |
|---|---|---|
| LMArena Math | 1402 | 1180 |
| Omni-MATH | — | 7.2% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Mistral: 16.6 (#288)
| Benchmark | DeepSeek-V3.1-Terminus | Mistral |
|---|---|---|
| MMLU-Pro | — | 27.7% |
| GPQA (HELM) | — | 30.3% |
| LMArena Expert | — | 1125 |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.1 (#92), Mistral: 32.8 (#254)
| Benchmark | DeepSeek-V3.1-Terminus | Mistral |
|---|---|---|
| LMArena Non-English | 1407 | 1129 |
| LMArena Russian | 1436 | 1168 |
| LMArena Chinese | — | 1109 |
| LMArena French | — | 1180 |
| LMArena German | — | 1155 |
| LMArena Japanese | — | 1013 |
| LMArena Korean | — | 1032 |
| LMArena Spanish | — | 1143 |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.0 (#106), Mistral: 52.6 (#288)
| Benchmark | DeepSeek-V3.1-Terminus | Mistral |
|---|---|---|
| LMArena Instruction Following | 1404 | 1152 |
| IFEval | — | 56.8% |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.4 (#97), Mistral: 35.0 (#245)
| Benchmark | DeepSeek-V3.1-Terminus | Mistral |
|---|---|---|
| LMArena Longer Query | 1421 | 1153 |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.0 (#92), Mistral: 37.0 (#260)
| Benchmark | DeepSeek-V3.1-Terminus | Mistral |
|---|---|---|
| LMArena Text | 1419 | 1165 |
| LMArena Creative Writing | 1403 | 1158 |
| LMArena Multi-Turn | 1411 | 1147 |
| WildBench | — | 66% |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Mistral?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 29.9 on the Noometry Index.
Is DeepSeek-V3.1-Terminus or Mistral better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 42.0 versus 33.8 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1-Terminus and Mistral share?
10 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Mistral has 22.