Model comparison
DeepSeek-V3.2-Exp vs Mistral Small 3.1
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.9 to 31.4 on the Noometry Index.
Last verified . 22 shared benchmarks.
DeepSeek
Mistral AISummary
- They share 22 benchmarks with published results for both. DeepSeek-V3.2-Exp scores higher in 8 categories and Mistral Small 3.1 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek-V3.2-Exp leads 51.6 to 22.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 87.8% for DeepSeek-V3.2-Exp and 3.9% for Mistral Small 3.1.
- DeepSeek-V3.2-Exp is cheaper at $0.26 / $0.38 per million input/output tokens, against $0.35 / $0.56 for Mistral Small 3.1.
- DeepSeek-V3.2-Exp accepts more context: 164K tokens versus 128K.
Side by side
| DeepSeek-V3.2-Exp | Mistral Small 3.1 | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 44.9 | 31.4 |
| Released | 2025-09-29 | 2025-03-17 |
| Weights | Open | Open |
| Context window | 164K | 128K |
| Max output | 66K | 102K |
| Input $ / M tokens | $0.26 | $0.35 |
| Output $ / M tokens | $0.38 | $0.56 |
| Results tracked | 48 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 46.4 (#61), Mistral Small 3.1: 37.7 (#175)
| Benchmark | DeepSeek-V3.2-Exp | Mistral Small 3.1 |
|---|---|---|
| LMArena Coding | 1454 | 1309 |
| SWE-bench Verified (bash only) | 70% | — |
| Aider Polyglot | 74.2% | — |
| LMArena WebDev | 1362 | — |
| SWE-bench Multilingual | 59% | — |
| SciCode | 38.9% | — |
| WeirdML | 39.5% | — |
Agentic & Tool Use Not comparable
DeepSeek-V3.2-Exp: 37.9 (#31), Mistral Small 3.1: —
| Benchmark | DeepSeek-V3.2-Exp | Mistral Small 3.1 |
|---|---|---|
| Terminal-Bench | 39.6% | — |
| Berkeley Function Calling Leaderboard | 56.7% | — |
| TheAgentCompany | 42.9% | — |
| Vending-Bench 2 | 1,034 | — |
Reasoning DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 22.0 (#185), Mistral Small 3.1: 18.9 (#249)
| Benchmark | DeepSeek-V3.2-Exp | Mistral Small 3.1 |
|---|---|---|
| Chess Puzzles | 14% | 1% |
| LMArena Hard Prompts | 1433 | 1278 |
| Epoch Capabilities Index | 146.28 | 127.48 |
| ARC-AGI-2 | 4% | — |
| Kagi LLM Benchmark | 52.2% | — |
| NYT Connections (extended) | 36.7% | — |
| ARC-AGI-1 | 57% | — |
| CritPt | 2.9% | — |
| Thematic Generalization | 65% | — |
| DTBench | 87.7% | — |
| LMCA | 29.1% | — |
Math DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 40.8 (#75), Mistral Small 3.1: 13.7 (#295)
| Benchmark | DeepSeek-V3.2-Exp | Mistral Small 3.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 87.8% | 3.9% |
| LMArena Math | 1435 | 1261 |
| MathArena Final-Answer Competitions | 57.7% | — |
| ProofBench | 8% | — |
| Omni-MATH | — | 24.8% |
| FrontierMath (Feb 2025 set) | 22.1% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 51.6 (#61), Mistral Small 3.1: 22.6 (#266)
| Benchmark | DeepSeek-V3.2-Exp | Mistral Small 3.1 |
|---|---|---|
| GPQA Diamond | 83.4% | 41.9% |
| LMArena Expert | 1436 | 1258 |
| MMLU-Pro | — | 61% |
| Vectara Hallucination Rate | 5.3% | — |
| GPQA (HELM) | — | 39.2% |
Multimodal Not comparable
DeepSeek-V3.2-Exp: —, Mistral Small 3.1: 32.6 (#93)
| Benchmark | DeepSeek-V3.2-Exp | Mistral Small 3.1 |
|---|---|---|
| LMArena Vision | — | 1136 |
Multilingual DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 52.4 (#85), Mistral Small 3.1: 41.4 (#204)
| Benchmark | DeepSeek-V3.2-Exp | Mistral Small 3.1 |
|---|---|---|
| LMArena Non-English | 1409 | 1255 |
| LMArena Chinese | 1461 | 1254 |
| LMArena French | 1435 | 1270 |
| LMArena German | 1440 | 1266 |
| LMArena Japanese | 1377 | 1210 |
| LMArena Korean | 1372 | 1206 |
| LMArena Russian | 1423 | 1263 |
| LMArena Spanish | 1441 | 1283 |
Instruction Following DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 74.7 (#89), Mistral Small 3.1: 63.8 (#225)
| Benchmark | DeepSeek-V3.2-Exp | Mistral Small 3.1 |
|---|---|---|
| LMArena Instruction Following | 1413 | 1264 |
| IFEval | — | 75% |
Long Context DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 47.6 (#15), Mistral Small 3.1: 39.5 (#172)
| Benchmark | DeepSeek-V3.2-Exp | Mistral Small 3.1 |
|---|---|---|
| LMArena Longer Query | 1428 | 1300 |
| Fiction.LiveBench | 83.3% | — |
| CL-bench | 13.2% | — |
| CL-bench Life | 9.5% | — |
Writing & Preference DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 62.5 (#73), Mistral Small 3.1: 37.2 (#254)
| Benchmark | DeepSeek-V3.2-Exp | Mistral Small 3.1 |
|---|---|---|
| LMArena Text | 1425 | 1278 |
| LMArena Creative Writing | 1403 | 1253 |
| EQ-Bench Creative Writing | 1515 | 761 |
| LMArena Multi-Turn | 1427 | 1270 |
| WildBench | — | 78.8% |
Frequently asked questions
Is DeepSeek-V3.2-Exp better than Mistral Small 3.1?
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.9 to 31.4 on the Noometry Index.
Which is cheaper, DeepSeek-V3.2-Exp or Mistral Small 3.1?
DeepSeek-V3.2-Exp is cheaper. It lists at $0.26 per million input tokens and $0.38 per million output tokens; Mistral Small 3.1 lists at $0.35 and $0.56.
Is DeepSeek-V3.2-Exp or Mistral Small 3.1 better for coding?
DeepSeek-V3.2-Exp scores higher on coding benchmarks: 46.4 versus 37.7 in the Noometry coding category.
Which has the bigger context window?
DeepSeek-V3.2-Exp does, with 164K tokens against 128K.
How many benchmarks do DeepSeek-V3.2-Exp and Mistral Small 3.1 share?
22 benchmarks have published results for both models. DeepSeek-V3.2-Exp has 48 scored results on Noometry and Mistral Small 3.1 has 28.