Model comparison
GPT-4 Turbo vs Mistral Small 3
GPT-4 Turbo and Mistral Small 3 score almost the same on the Noometry Index (30.3 vs 30.9), so choose on price, context window or the category you care about most.
Last verified . 23 shared benchmarks.
Mistral AISummary
- They share 23 benchmarks with published results for both. GPT-4 Turbo scores higher in 4 categories and Mistral Small 3 in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-4 Turbo leads 47.9 to 32.4.
- The biggest single-benchmark swing is BigCodeBench Complete: 58.2% for GPT-4 Turbo and 50.4% for Mistral Small 3.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
- GPT-4 Turbo accepts more context: 128K tokens versus 33K.
- Mistral Small 3 has downloadable open weights; the other is API-only.
Side by side
| GPT-4 Turbo | Mistral Small 3 | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 30.3 | 30.9 |
| Released | 2023-11-06 | 2025-01-30 |
| Weights | Proprietary | Open |
| Context window | 128K | 33K |
| Max output | 4K | 16K |
| Input $ / M tokens | $10 | $0.05 |
| Output $ / M tokens | $30 | $0.08 |
| Results tracked | 36 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small 3 leads
GPT-4 Turbo: 33.4 (#247), Mistral Small 3: 36.0 (#203)
| Benchmark | GPT-4 Turbo | Mistral Small 3 |
|---|---|---|
| BigCodeBench Instruct | 48.2% | 45.3% |
| LMArena Coding | 1268 | 1246 |
| BigCodeBench Complete | 58.2% | 50.4% |
| WeirdML | 18% | — |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Not comparable
GPT-4 Turbo: —, Mistral Small 3: —
| Benchmark | GPT-4 Turbo | Mistral Small 3 |
|---|---|---|
| METR Time Horizons | 36.7% | — |
Reasoning Mistral Small 3 leads
GPT-4 Turbo: 14.9 (#311), Mistral Small 3: 18.2 (#269)
| Benchmark | GPT-4 Turbo | Mistral Small 3 |
|---|---|---|
| Chess Puzzles | 6% | 0% |
| LMArena Hard Prompts | 1251 | 1233 |
| Epoch Capabilities Index | 127.25 | 127.06 |
| SimpleBench | 25.1% | — |
| DTBench | 61.6% | — |
| LMCA | 9.8% | — |
| ForecastBench | 59.4 | — |
Math Mistral Small 3 leads
GPT-4 Turbo: 8.6 (#316), Mistral Small 3: 15.3 (#290)
| Benchmark | GPT-4 Turbo | Mistral Small 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.7% | 6.7% |
| LMArena Math | 1272 | 1240 |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| MATH Level 5 | 46.7% | — |
Knowledge Too close to call
GPT-4 Turbo: 24.3 (#263), Mistral Small 3: 25.0 (#258)
| Benchmark | GPT-4 Turbo | Mistral Small 3 |
|---|---|---|
| GPQA Diamond | 46.6% | 47.3% |
| Confabulations | 28.4% | 25.2% |
| LMArena Expert | 1223 | 1202 |
| MMLU | 81.3% | — |
Multimodal Not comparable
GPT-4 Turbo: 30.0 (#104), Mistral Small 3: —
| Benchmark | GPT-4 Turbo | Mistral Small 3 |
|---|---|---|
| LMArena Vision | 1090 | — |
Multilingual GPT-4 Turbo leads
GPT-4 Turbo: 40.7 (#211), Mistral Small 3: 37.5 (#231)
| Benchmark | GPT-4 Turbo | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1245 | 1198 |
| LMArena Chinese | 1242 | 1204 |
| LMArena French | 1275 | 1202 |
| LMArena German | 1259 | 1211 |
| LMArena Japanese | 1194 | 1111 |
| LMArena Korean | 1187 | 1188 |
| LMArena Russian | 1259 | 1216 |
| LMArena Spanish | 1260 | — |
Instruction Following GPT-4 Turbo leads
GPT-4 Turbo: 66.0 (#211), Mistral Small 3: 63.9 (#224)
| Benchmark | GPT-4 Turbo | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1250 | 1214 |
Long Context Too close to call
GPT-4 Turbo: 38.0 (#200), Mistral Small 3: 37.8 (#206)
| Benchmark | GPT-4 Turbo | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1254 | 1246 |
Writing & Preference GPT-4 Turbo leads
GPT-4 Turbo: 47.9 (#201), Mistral Small 3: 32.4 (#275)
| Benchmark | GPT-4 Turbo | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1272 | 1234 |
| LMArena Creative Writing | 1269 | 1195 |
| LMArena Multi-Turn | 1267 | 1217 |
| EQ-Bench Creative Writing | — | 707 |
Frequently asked questions
Is GPT-4 Turbo better than Mistral Small 3?
GPT-4 Turbo and Mistral Small 3 score almost the same on the Noometry Index (30.3 vs 30.9), so choose on price, context window or the category you care about most.
Which is cheaper, GPT-4 Turbo 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 Turbo lists at $10 and $30.
Is GPT-4 Turbo or Mistral Small 3 better for coding?
Mistral Small 3 scores higher on coding benchmarks: 36.0 versus 33.4 in the Noometry coding category.
Which has the bigger context window?
GPT-4 Turbo does, with 128K tokens against 33K.
How many benchmarks do GPT-4 Turbo and Mistral Small 3 share?
23 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Mistral Small 3 has 24.