Model comparison
GPT-4.1 vs Mistral Small 3
GPT-4.1 is the stronger model overall, scoring 35.7 to 30.9 on the Noometry Index. Mistral Small 3 costs 61× less per token, which makes it the better buy when GPT-4.1's lead doesn't matter for your workload.
Last verified . 21 shared benchmarks.
Mistral AISummary
- They share 21 benchmarks with published results for both. GPT-4.1 scores higher in 6 categories and Mistral Small 3 in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-4.1 leads 57.8 to 32.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 38.3% for GPT-4.1 and 6.7% for Mistral Small 3.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $2 / $8 for GPT-4.1.
- GPT-4.1 accepts more context: 1.05M tokens versus 33K.
- Mistral Small 3 has downloadable open weights; the other is API-only.
Side by side
| GPT-4.1 | Mistral Small 3 | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 35.7 | 30.9 |
| Released | 2025-04-14 | 2025-01-30 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 33K |
| Max output | 33K | 16K |
| Input $ / M tokens | $2 | $0.05 |
| Output $ / M tokens | $8 | $0.08 |
| Results tracked | 52 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small 3 leads
GPT-4.1: 34.2 (#228), Mistral Small 3: 36.0 (#203)
| Benchmark | GPT-4.1 | Mistral Small 3 |
|---|---|---|
| LMArena Coding | 1391 | 1246 |
| SWE-bench Verified | 48.5% | — |
| SWE-bench Verified (bash only) | 39.6% | — |
| Aider Polyglot | 52.4% | — |
| WeirdML | 39% | — |
| BigCodeBench Instruct | — | 45.3% |
| BigCodeBench Complete | — | 50.4% |
| CadEval | 42% | — |
| ALE-Bench | 558.1 | — |
Agentic & Tool Use Not comparable
GPT-4.1: 34.4 (#40), Mistral Small 3: —
| Benchmark | GPT-4.1 | Mistral Small 3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 54% | — |
Reasoning Mistral Small 3 leads
GPT-4.1: 11.7 (#334), Mistral Small 3: 18.2 (#269)
| Benchmark | GPT-4.1 | Mistral Small 3 |
|---|---|---|
| Chess Puzzles | 6% | 0% |
| LMArena Hard Prompts | 1384 | 1233 |
| Epoch Capabilities Index | 136.79 | 127.06 |
| ARC-AGI-2 | 0.4% | — |
| SimpleBench | 27% | — |
| Kagi LLM Benchmark | 52.3% | — |
| ARC-AGI-1 | 5.5% | — |
| EnigmaEval | 2.2% | — |
| DTBench | 68.3% | — |
| LMCA | 25.6% | — |
| ForecastBench | 61.5 | — |
Math GPT-4.1 leads
GPT-4.1: 21.4 (#269), Mistral Small 3: 15.3 (#290)
| Benchmark | GPT-4.1 | Mistral Small 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 38.3% | 6.7% |
| LMArena Math | 1369 | 1240 |
| FrontierMath (Tiers 1-3) | 6% | — |
| Omni-MATH | 47.1% | — |
| MATH Level 5 | 83% | — |
| FrontierMath (Feb 2025 set) | 5.5% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge GPT-4.1 leads
GPT-4.1: 37.0 (#152), Mistral Small 3: 25.0 (#258)
| Benchmark | GPT-4.1 | Mistral Small 3 |
|---|---|---|
| GPQA Diamond | 66.9% | 47.3% |
| LMArena Expert | 1364 | 1202 |
| Humanity's Last Exam | 5.4% | — |
| SimpleQA Verified | 31.1% | — |
| MMLU-Pro | 81.1% | — |
| Confabulations | — | 25.2% |
| Vectara Hallucination Rate | 5.6% | — |
| GPQA (HELM) | 65.9% | — |
Multimodal Not comparable
GPT-4.1: 37.5 (#66), Mistral Small 3: —
| Benchmark | GPT-4.1 | Mistral Small 3 |
|---|---|---|
| LMArena Vision | 1210 | — |
| GeoBench | 72% | — |
Multilingual GPT-4.1 leads
GPT-4.1: 49.6 (#128), Mistral Small 3: 37.5 (#231)
| Benchmark | GPT-4.1 | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1370 | 1198 |
| LMArena Chinese | 1382 | 1204 |
| LMArena French | 1383 | 1202 |
| LMArena German | 1380 | 1211 |
| LMArena Japanese | 1320 | 1111 |
| LMArena Korean | 1339 | 1188 |
| LMArena Russian | 1377 | 1216 |
| LMArena Spanish | 1375 | — |
Instruction Following GPT-4.1 leads
GPT-4.1: 71.5 (#148), Mistral Small 3: 63.9 (#224)
| Benchmark | GPT-4.1 | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1367 | 1214 |
| IFEval | 83.8% | — |
Long Context GPT-4.1 leads
GPT-4.1: 40.0 (#158), Mistral Small 3: 37.8 (#206)
| Benchmark | GPT-4.1 | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1385 | 1246 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference GPT-4.1 leads
GPT-4.1: 57.8 (#120), Mistral Small 3: 32.4 (#275)
| Benchmark | GPT-4.1 | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1383 | 1234 |
| LMArena Creative Writing | 1363 | 1195 |
| EQ-Bench Creative Writing | 1420 | 707 |
| LMArena Multi-Turn | 1398 | 1217 |
| WildBench | 85.4% | — |
Frequently asked questions
Is GPT-4.1 better than Mistral Small 3?
GPT-4.1 is the stronger model overall, scoring 35.7 to 30.9 on the Noometry Index. Mistral Small 3 costs 61× less per token, which makes it the better buy when GPT-4.1's lead doesn't matter for your workload.
Which is cheaper, GPT-4.1 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-4.1 lists at $2 and $8.
Is GPT-4.1 or Mistral Small 3 better for coding?
Mistral Small 3 scores higher on coding benchmarks: 36.0 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 does, with 1.05M tokens against 33K.
How many benchmarks do GPT-4.1 and Mistral Small 3 share?
21 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and Mistral Small 3 has 24.