Model comparison
DeepSeek-V3.2-Exp vs Mistral Small 3.2
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.9 to 30.8 on the Noometry Index. Mistral Small 3.2 costs 2.2× less per token, which makes it the better buy when DeepSeek-V3.2-Exp's lead doesn't matter for your workload.
Last verified . 6 shared benchmarks.
DeepSeek
Mistral AISummary
- They share 6 benchmarks with published results for both. DeepSeek-V3.2-Exp scores higher in 4 categories and Mistral Small 3.2 in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek-V3.2-Exp leads 51.6 to 26.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 87.8% for DeepSeek-V3.2-Exp and 30.3% for Mistral Small 3.2.
- Mistral Small 3.2 is cheaper at $0.0938 / $0.25 per million input/output tokens, against $0.26 / $0.38 for DeepSeek-V3.2-Exp.
- Mistral Small 3.2 accepts more context: 256K tokens versus 164K.
Side by side
| DeepSeek-V3.2-Exp | Mistral Small 3.2 | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 44.9 | 30.8 |
| Released | 2025-09-29 | 2025-06-20 |
| Weights | Open | Open |
| Context window | 164K | 256K |
| Max output | 66K | 16K |
| Input $ / M tokens | $0.26 | $0.0938 |
| Output $ / M tokens | $0.38 | $0.25 |
| Results tracked | 48 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
DeepSeek-V3.2-Exp: 46.4 (#61), Mistral Small 3.2: —
| Benchmark | DeepSeek-V3.2-Exp | Mistral Small 3.2 |
|---|---|---|
| SWE-bench Verified (bash only) | 70% | — |
| Aider Polyglot | 74.2% | — |
| LMArena WebDev | 1362 | — |
| SWE-bench Multilingual | 59% | — |
| SciCode | 38.9% | — |
| WeirdML | 39.5% | — |
| LMArena Coding | 1454 | — |
Agentic & Tool Use Not comparable
DeepSeek-V3.2-Exp: 37.9 (#31), Mistral Small 3.2: —
| Benchmark | DeepSeek-V3.2-Exp | Mistral Small 3.2 |
|---|---|---|
| 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 3.2: 17.5 (#282)
| Benchmark | DeepSeek-V3.2-Exp | Mistral Small 3.2 |
|---|---|---|
| Kagi LLM Benchmark | 52.2% | 40.4% |
| Chess Puzzles | 14% | 1% |
| Epoch Capabilities Index | 146.28 | 131.73 |
| ARC-AGI-2 | 4% | — |
| NYT Connections (extended) | 36.7% | — |
| ARC-AGI-1 | 57% | — |
| CritPt | 2.9% | — |
| Thematic Generalization | 65% | — |
| LMArena Hard Prompts | 1433 | — |
| DTBench | 87.7% | — |
| LMCA | 29.1% | — |
Math DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 40.8 (#75), Mistral Small 3.2: 24.9 (#251)
| Benchmark | DeepSeek-V3.2-Exp | Mistral Small 3.2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 87.8% | 30.3% |
| MathArena Final-Answer Competitions | 57.7% | — |
| ProofBench | 8% | — |
| LMArena Math | 1435 | — |
| 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 3.2: 26.8 (#249)
| Benchmark | DeepSeek-V3.2-Exp | Mistral Small 3.2 |
|---|---|---|
| GPQA Diamond | 83.4% | 49.1% |
| Vectara Hallucination Rate | 5.3% | — |
| LMArena Expert | 1436 | — |
Multilingual Not comparable
DeepSeek-V3.2-Exp: 52.4 (#85), Mistral Small 3.2: —
| Benchmark | DeepSeek-V3.2-Exp | Mistral Small 3.2 |
|---|---|---|
| LMArena Non-English | 1409 | — |
| LMArena Chinese | 1461 | — |
| LMArena French | 1435 | — |
| LMArena German | 1440 | — |
| LMArena Japanese | 1377 | — |
| LMArena Korean | 1372 | — |
| LMArena Russian | 1423 | — |
| LMArena Spanish | 1441 | — |
Instruction Following Not comparable
DeepSeek-V3.2-Exp: 74.7 (#89), Mistral Small 3.2: —
| Benchmark | DeepSeek-V3.2-Exp | Mistral Small 3.2 |
|---|---|---|
| LMArena Instruction Following | 1413 | — |
Long Context Not comparable
DeepSeek-V3.2-Exp: 47.6 (#15), Mistral Small 3.2: —
| Benchmark | DeepSeek-V3.2-Exp | Mistral Small 3.2 |
|---|---|---|
| Fiction.LiveBench | 83.3% | — |
| CL-bench | 13.2% | — |
| CL-bench Life | 9.5% | — |
| LMArena Longer Query | 1428 | — |
Writing & Preference DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 62.5 (#73), Mistral Small 3.2: 45.1 (#219)
| Benchmark | DeepSeek-V3.2-Exp | Mistral Small 3.2 |
|---|---|---|
| EQ-Bench Creative Writing | 1515 | 1255 |
| LMArena Text | 1425 | — |
| LMArena Creative Writing | 1403 | — |
| LMArena Multi-Turn | 1427 | — |
Frequently asked questions
Is DeepSeek-V3.2-Exp better than Mistral Small 3.2?
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.9 to 30.8 on the Noometry Index. Mistral Small 3.2 costs 2.2× less per token, which makes it the better buy when DeepSeek-V3.2-Exp's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-V3.2-Exp or Mistral Small 3.2?
Mistral Small 3.2 is cheaper. It lists at $0.0938 per million input tokens and $0.25 per million output tokens; DeepSeek-V3.2-Exp lists at $0.26 and $0.38.
Which has the bigger context window?
Mistral Small 3.2 does, with 256K tokens against 164K.
How many benchmarks do DeepSeek-V3.2-Exp and Mistral Small 3.2 share?
6 benchmarks have published results for both models. DeepSeek-V3.2-Exp has 48 scored results on Noometry and Mistral Small 3.2 has 6.