Model comparison
GPT-4 Turbo vs Magistral Medium
Magistral Medium is the stronger model overall, scoring 35.2 to 30.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AISummary
- They share 17 benchmarks with published results for both. GPT-4 Turbo scores higher in 3 categories and Magistral Medium in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Magistral Medium leads 35.1 to 9.0.
- Magistral Medium is cheaper at $2 / $5 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
- Magistral Medium accepts more context: 262K tokens versus 128K.
- Magistral Medium has downloadable open weights; the other is API-only.
Side by side
| GPT-4 Turbo | Magistral Medium | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 30.5 | 35.2 |
| Released | 2023-11-06 | 2025-03-17 |
| Weights | Proprietary | Open |
| Context window | 128K | 262K |
| Max output | 4K | 16K |
| Input $ / M tokens | $10 | $2 |
| Output $ / M tokens | $30 | $5 |
| Results tracked | 36 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Magistral Medium leads
GPT-4 Turbo: 33.8 (#249), Magistral Medium: 39.1 (#161)
| Benchmark | GPT-4 Turbo | Magistral Medium |
|---|---|---|
| LMArena Coding | 1268 | 1319 |
| SciCode | — | 39.2% |
| WeirdML | 18% | — |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 58.2% | — |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Not comparable
GPT-4 Turbo: —, Magistral Medium: —
| Benchmark | GPT-4 Turbo | Magistral Medium |
|---|---|---|
| METR Time Horizons | 36.7% | — |
Reasoning GPT-4 Turbo leads
GPT-4 Turbo: 15.3 (#317), Magistral Medium: 8.6 (#348)
| Benchmark | GPT-4 Turbo | Magistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1251 | 1267 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | 25.1% | — |
| Kagi LLM Benchmark | — | 16.2% |
| ARC-AGI-1 | — | 6.1% |
| CritPt | — | 0.3% |
| Chess Puzzles | 6% | — |
| DTBench | 61.6% | — |
| LMCA | 9.8% | — |
| Epoch Capabilities Index | 127.25 | — |
| ForecastBench | 59.4 | — |
Math Magistral Medium leads
GPT-4 Turbo: 9.0 (#322), Magistral Medium: 35.1 (#189)
| Benchmark | GPT-4 Turbo | Magistral Medium |
|---|---|---|
| LMArena Math | 1272 | 1250 |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| OTIS Mock AIME 2024-2025 | 6.7% | — |
| MATH Level 5 | 46.7% | — |
Knowledge Magistral Medium leads
GPT-4 Turbo: 24.3 (#268), Magistral Medium: 33.5 (#202)
| Benchmark | GPT-4 Turbo | Magistral Medium |
|---|---|---|
| LMArena Expert | 1223 | 1223 |
| GPQA Diamond | 46.6% | — |
| Confabulations | 28.4% | — |
| MMLU | 81.3% | — |
Multimodal Not comparable
GPT-4 Turbo: 30.6 (#110), Magistral Medium: —
| Benchmark | GPT-4 Turbo | Magistral Medium |
|---|---|---|
| LMArena Vision | 1090 | — |
Multilingual Too close to call
GPT-4 Turbo: 40.5 (#216), Magistral Medium: 39.6 (#224)
| Benchmark | GPT-4 Turbo | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1245 | 1232 |
| LMArena Chinese | 1242 | 1227 |
| LMArena French | 1276 | 1267 |
| LMArena German | 1259 | 1248 |
| LMArena Japanese | 1194 | 1175 |
| LMArena Korean | 1187 | 1125 |
| LMArena Russian | 1259 | 1224 |
| LMArena Spanish | 1260 | 1271 |
Instruction Following Too close to call
GPT-4 Turbo: 65.8 (#216), Magistral Medium: 66.0 (#211)
| Benchmark | GPT-4 Turbo | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1249 | 1254 |
Long Context Magistral Medium leads
GPT-4 Turbo: 38.0 (#206), Magistral Medium: 39.3 (#183)
| Benchmark | GPT-4 Turbo | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1254 | 1295 |
Writing & Preference GPT-4 Turbo leads
GPT-4 Turbo: 47.7 (#206), Magistral Medium: 46.3 (#219)
| Benchmark | GPT-4 Turbo | Magistral Medium |
|---|---|---|
| LMArena Text | 1272 | 1255 |
| LMArena Creative Writing | 1269 | 1245 |
| LMArena Multi-Turn | 1267 | 1275 |
Frequently asked questions
Is GPT-4 Turbo better than Magistral Medium?
Magistral Medium is the stronger model overall, scoring 35.2 to 30.5 on the Noometry Index.
Which is cheaper, GPT-4 Turbo or Magistral Medium?
Magistral Medium is cheaper. It lists at $2 per million input tokens and $5 per million output tokens; GPT-4 Turbo lists at $10 and $30.
Is GPT-4 Turbo or Magistral Medium better for coding?
Magistral Medium scores higher on coding benchmarks: 39.1 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
Magistral Medium does, with 262K tokens against 128K.
How many benchmarks do GPT-4 Turbo and Magistral Medium share?
17 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Magistral Medium has 22.