Model comparison
GPT-5 Nano vs Mistral Small 3
GPT-5 Nano is the stronger model overall, scoring 33.5 to 31.2 on the Noometry Index. Mistral Small 3 costs 2.4× less per token, which makes it the better buy when GPT-5 Nano's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
Mistral AISummary
- They share 20 benchmarks with published results for both. GPT-5 Nano scores higher in 5 categories and Mistral Small 3 in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5 Nano leads 29.4 to 16.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 81.1% for GPT-5 Nano and 6.7% for Mistral Small 3.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.05 / $0.40 for GPT-5 Nano.
- GPT-5 Nano accepts more context: 400K tokens versus 33K.
- Mistral Small 3 has downloadable open weights; the other is API-only.
Side by side
| GPT-5 Nano | Mistral Small 3 | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 33.5 | 31.2 |
| Released | 2025-08-07 | 2025-01-30 |
| Weights | Proprietary | Open |
| Context window | 400K | 33K |
| Max output | 128K | 16K |
| Input $ / M tokens | $0.05 | $0.05 |
| Output $ / M tokens | $0.40 | $0.08 |
| Results tracked | 49 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small 3 leads
GPT-5 Nano: 33.6 (#254), Mistral Small 3: 36.5 (#207)
| Benchmark | GPT-5 Nano | Mistral Small 3 |
|---|---|---|
| LMArena Coding | 1351 | 1246 |
| SWE-bench Verified (bash only) | 34.8% | — |
| WeirdML | 38.1% | — |
| BigCodeBench Instruct | — | 45.3% |
| BigCodeBench Complete | — | 50.4% |
| ALE-Bench | 718.67 | — |
Agentic & Tool Use Not comparable
GPT-5 Nano: 25.8 (#106), Mistral Small 3: —
| Benchmark | GPT-5 Nano | Mistral Small 3 |
|---|---|---|
| Terminal-Bench | 21.8% | — |
| Berkeley Function Calling Leaderboard | 51.5% | — |
Reasoning Mistral Small 3 leads
GPT-5 Nano: 16.3 (#306), Mistral Small 3: 18.9 (#273)
| Benchmark | GPT-5 Nano | Mistral Small 3 |
|---|---|---|
| Chess Puzzles | 27% | 0% |
| LMArena Hard Prompts | 1328 | 1233 |
| Epoch Capabilities Index | 139.38 | 127.07 |
| ARC-AGI-2 | 2.6% | — |
| Kagi LLM Benchmark | 62.2% | — |
| ARC-AGI-1 | 20.7% | — |
| Mystery Game Puzzles | 9% | — |
| DTBench | 62.7% | — |
| LMCA | 7.9% | — |
| ForecastBench | 59.1 | — |
Math GPT-5 Nano leads
GPT-5 Nano: 29.4 (#241), Mistral Small 3: 16.3 (#295)
| Benchmark | GPT-5 Nano | Mistral Small 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 81.1% | 6.7% |
| LMArena Math | 1317 | 1240 |
| FrontierMath (Tiers 1-3) | 20% | — |
| FrontierMath Tier 4 | 2.4% | — |
| ProofBench | 12% | — |
| Omni-MATH | 54.6% | — |
| MATH Level 5 | 95.2% | — |
| FrontierMath (Feb 2025 set) | 8.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GPT-5 Nano leads
GPT-5 Nano: 35.9 (#178), Mistral Small 3: 25.1 (#263)
| Benchmark | GPT-5 Nano | Mistral Small 3 |
|---|---|---|
| GPQA Diamond | 69.4% | 47.3% |
| LMArena Expert | 1321 | 1202 |
| SimpleQA Verified | 11.7% | — |
| MMLU-Pro | 77.8% | — |
| Confabulations | — | 25.2% |
| Vectara Hallucination Rate | 10.5% | — |
| GPQA (HELM) | 67.9% | — |
Multimodal Not comparable
GPT-5 Nano: 31.3 (#108), Mistral Small 3: —
| Benchmark | GPT-5 Nano | Mistral Small 3 |
|---|---|---|
| LMArena Vision | 1159 | — |
| VPCT | 37.2% | — |
Multilingual GPT-5 Nano leads
GPT-5 Nano: 45.3 (#172), Mistral Small 3: 37.3 (#236)
| Benchmark | GPT-5 Nano | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1313 | 1198 |
| LMArena Chinese | 1356 | 1204 |
| LMArena German | 1327 | 1211 |
| LMArena Japanese | 1226 | 1111 |
| LMArena Korean | 1269 | 1188 |
| LMArena Russian | 1296 | 1216 |
| LMArena French | — | 1203 |
| LMArena Spanish | 1360 | — |
Instruction Following GPT-5 Nano leads
GPT-5 Nano: 75.0 (#79), Mistral Small 3: 63.7 (#229)
| Benchmark | GPT-5 Nano | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1306 | 1214 |
| IFEval | 93.2% | — |
Long Context Mistral Small 3 leads
GPT-5 Nano: 31.3 (#281), Mistral Small 3: 37.8 (#211)
| Benchmark | GPT-5 Nano | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1312 | 1246 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference GPT-5 Nano leads
GPT-5 Nano: 39.1 (#249), Mistral Small 3: 32.2 (#280)
| Benchmark | GPT-5 Nano | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1320 | 1234 |
| LMArena Creative Writing | 1249 | 1195 |
| EQ-Bench Creative Writing | 705 | 707 |
| LMArena Multi-Turn | 1311 | 1217 |
| WildBench | 80.6% | — |
Frequently asked questions
Is GPT-5 Nano better than Mistral Small 3?
GPT-5 Nano is the stronger model overall, scoring 33.5 to 31.2 on the Noometry Index. Mistral Small 3 costs 2.4× less per token, which makes it the better buy when GPT-5 Nano's lead doesn't matter for your workload.
Which is cheaper, GPT-5 Nano or Mistral Small 3?
Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; GPT-5 Nano lists at $0.05 and $0.40.
Is GPT-5 Nano or Mistral Small 3 better for coding?
Mistral Small 3 scores higher on coding benchmarks: 36.5 versus 33.6 in the Noometry coding category.
Which has the bigger context window?
GPT-5 Nano does, with 400K tokens against 33K.
How many benchmarks do GPT-5 Nano and Mistral Small 3 share?
20 benchmarks have published results for both models. GPT-5 Nano has 49 scored results on Noometry and Mistral Small 3 has 24.