Model comparison
DeepSeek-V2.5 (Sep 2024) vs Mistral Small 3.1
DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 to 31.7 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeek
Mistral AISummary
- They share 17 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 7 categories and Mistral Small 3.1 in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek-V2.5 (Sep 2024) leads 35.9 to 14.7.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Mistral Small 3.1 | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 37.6 | 31.7 |
| Released | 2024-09-06 | 2025-03-17 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 102K |
| Input $ / M tokens | — | $0.35 |
| Output $ / M tokens | — | $0.56 |
| Results tracked | 22 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small 3.1 leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Mistral Small 3.1: 38.3 (#179)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Small 3.1 |
|---|---|---|
| LMArena Coding | 1309 | 1309 |
| Aider Polyglot | 17.8% | — |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Mistral Small 3.1: 19.7 (#254)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Small 3.1 |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1278 |
| Chess Puzzles | — | 1% |
| Epoch Capabilities Index | — | 127.48 |
Math DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Mistral Small 3.1: 14.7 (#301)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Small 3.1 |
|---|---|---|
| LMArena Math | 1288 | 1262 |
| OTIS Mock AIME 2024-2025 | — | 3.9% |
| Omni-MATH | — | 24.8% |
Knowledge DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Mistral Small 3.1: 22.6 (#271)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Small 3.1 |
|---|---|---|
| LMArena Expert | 1266 | 1257 |
| GPQA Diamond | — | 41.9% |
| MMLU-Pro | — | 61% |
| GPQA (HELM) | — | 39.2% |
Multimodal Not comparable
DeepSeek-V2.5 (Sep 2024): —, Mistral Small 3.1: 33.2 (#99)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Small 3.1 |
|---|---|---|
| LMArena Vision | — | 1136 |
Multilingual DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Mistral Small 3.1: 41.2 (#209)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Small 3.1 |
|---|---|---|
| LMArena Non-English | 1273 | 1255 |
| LMArena Chinese | 1318 | 1253 |
| LMArena French | 1289 | 1273 |
| LMArena German | 1258 | 1266 |
| LMArena Japanese | 1228 | 1208 |
| LMArena Korean | 1209 | 1206 |
| LMArena Russian | 1289 | 1263 |
| LMArena Spanish | 1248 | 1283 |
Instruction Following DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Mistral Small 3.1: 63.6 (#230)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Small 3.1 |
|---|---|---|
| LMArena Instruction Following | 1280 | 1264 |
| IFEval | — | 75% |
Long Context Too close to call
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Mistral Small 3.1: 39.5 (#178)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Small 3.1 |
|---|---|---|
| LMArena Longer Query | 1301 | 1299 |
Writing & Preference DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Mistral Small 3.1: 37.0 (#259)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Mistral Small 3.1 |
|---|---|---|
| LMArena Text | 1294 | 1277 |
| LMArena Creative Writing | 1285 | 1253 |
| LMArena Multi-Turn | 1297 | 1270 |
| EQ-Bench Creative Writing | — | 761 |
| WildBench | — | 78.8% |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Mistral Small 3.1?
DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 to 31.7 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Mistral Small 3.1 better for coding?
Mistral Small 3.1 scores higher on coding benchmarks: 38.3 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Mistral Small 3.1 share?
17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Mistral Small 3.1 has 28.