Model comparison
GPT-4 vs Mistral Medium 3.5
Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 29.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AISummary
- They share 17 benchmarks with published results for both. GPT-4 scores higher in 1 category and Mistral Medium 3.5 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral Medium 3.5 leads 39.1 to 10.8.
- Mistral Medium 3.5 is cheaper at $1.50 / $7.50 per million input/output tokens, against $30 / $60 for GPT-4.
- Mistral Medium 3.5 accepts more context: 262K tokens versus 8K.
- Mistral Medium 3.5 has downloadable open weights; the other is API-only.
Side by side
| GPT-4 | Mistral Medium 3.5 | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 29.1 | 40.2 |
| Released | 2023-03-14 | — |
| Weights | Proprietary | Open |
| Context window | 8K | 262K |
| Max output | 8K | 210K |
| Input $ / M tokens | $30 | $1.50 |
| Output $ / M tokens | $60 | $7.50 |
| Results tracked | 38 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Medium 3.5 leads
GPT-4: 31.6 (#283), Mistral Medium 3.5: 36.0 (#213)
| Benchmark | GPT-4 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Coding | 1254 | 1461 |
| LMArena WebDev | — | 1264 |
| WeirdML | 12.4% | — |
| BigCodeBench Instruct | 46% | — |
| BigCodeBench Complete | 57.2% | — |
| HumanEval+ | 79.3% | — |
Agentic & Tool Use Not comparable
GPT-4: —, Mistral Medium 3.5: —
| Benchmark | GPT-4 | Mistral Medium 3.5 |
|---|---|---|
| METR Time Horizons | 36.1% | — |
Reasoning Too close to call
GPT-4: 17.8 (#289), Mistral Medium 3.5: 17.3 (#295)
| Benchmark | GPT-4 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1436 |
| Epoch Capabilities Index | 125.89 | 141.35 |
| Kagi LLM Benchmark | — | 41.4% |
| NYT Connections (extended) | — | 12.9% |
| Chess Puzzles | 4% | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 62.7% | — |
| LMCA | 17.1% | — |
| BIG-Bench Hard | 75.1% | — |
| ForecastBench | 57.8 | — |
| HellaSwag | 95.3% | — |
| WinoGrande | 87.5% | — |
Math Mistral Medium 3.5 leads
GPT-4: 10.8 (#309), Mistral Medium 3.5: 39.1 (#113)
| Benchmark | GPT-4 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Math | 1269 | 1431 |
| OTIS Mock AIME 2024-2025 | 1.1% | — |
| MATH Level 5 | 23% | — |
| GSM8K | 92% | — |
Knowledge Mistral Medium 3.5 leads
GPT-4: 18.4 (#282), Mistral Medium 3.5: 40.0 (#126)
| Benchmark | GPT-4 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Expert | 1211 | 1432 |
| GPQA Diamond | 35.7% | — |
| MMLU | 86.4% | — |
| TriviaQA | 84.8% | — |
Multimodal Not comparable
GPT-4: —, Mistral Medium 3.5: 38.3 (#65)
| Benchmark | GPT-4 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Vision | — | 1223 |
Multilingual Mistral Medium 3.5 leads
GPT-4: 40.6 (#215), Mistral Medium 3.5: 51.9 (#100)
| Benchmark | GPT-4 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Non-English | 1246 | 1404 |
| LMArena Chinese | 1242 | 1442 |
| LMArena French | 1283 | 1448 |
| LMArena German | 1251 | 1451 |
| LMArena Korean | 1184 | 1385 |
| LMArena Russian | 1251 | 1395 |
| LMArena Spanish | 1261 | 1409 |
| LMArena Japanese | 1209 | — |
Instruction Following Mistral Medium 3.5 leads
GPT-4: 65.3 (#222), Mistral Medium 3.5: 74.6 (#90)
| Benchmark | GPT-4 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Instruction Following | 1241 | 1415 |
Long Context Mistral Medium 3.5 leads
GPT-4: 37.7 (#212), Mistral Medium 3.5: 43.2 (#103)
| Benchmark | GPT-4 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Longer Query | 1244 | 1415 |
Writing & Preference Mistral Medium 3.5 leads
GPT-4: 34.9 (#268), Mistral Medium 3.5: 58.5 (#117)
| Benchmark | GPT-4 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Text | 1263 | 1421 |
| LMArena Creative Writing | 1244 | 1374 |
| LMArena Multi-Turn | 1257 | 1423 |
| EQ-Bench Creative Writing | 752 | — |
| EQ-Bench 4 | — | 993 |
Frequently asked questions
Is GPT-4 better than Mistral Medium 3.5?
Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 29.1 on the Noometry Index.
Which is cheaper, GPT-4 or Mistral Medium 3.5?
Mistral Medium 3.5 is cheaper. It lists at $1.50 per million input tokens and $7.50 per million output tokens; GPT-4 lists at $30 and $60.
Is GPT-4 or Mistral Medium 3.5 better for coding?
Mistral Medium 3.5 scores higher on coding benchmarks: 36.0 versus 31.6 in the Noometry coding category.
Which has the bigger context window?
Mistral Medium 3.5 does, with 262K tokens against 8K.
How many benchmarks do GPT-4 and Mistral Medium 3.5 share?
17 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Mistral Medium 3.5 has 22.