Model comparison
GPT-4 Turbo vs Magistral Small
GPT-4 Turbo and Magistral Small score almost the same on the Noometry Index (30.5 vs 30.2), so choose on price, context window or the category you care about most.
Last verified . 5 shared benchmarks.
Mistral AISummary
- They share 5 benchmarks with published results for both. GPT-4 Turbo scores higher in 1 category and Magistral Small in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where Magistral Small leads 26.2 to 9.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.7% for GPT-4 Turbo and 30% for Magistral Small.
- Magistral Small is cheaper at $0.50 / $1.50 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
- Magistral Small has downloadable open weights; the other is API-only.
Side by side
| GPT-4 Turbo | Magistral Small | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 30.5 | 30.2 |
| Released | 2023-11-06 | 2025-06-10 |
| Weights | Proprietary | Open |
| Context window | 128K | 128K |
| Max output | 4K | 40K |
| Input $ / M tokens | $10 | $0.50 |
| Output $ / M tokens | $30 | $1.50 |
| Results tracked | 36 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Magistral Small leads
GPT-4 Turbo: 33.8 (#249), Magistral Small: 38.4 (#176)
| Benchmark | GPT-4 Turbo | Magistral Small |
|---|---|---|
| SciCode | — | 35.2% |
| WeirdML | 18% | — |
| BigCodeBench Instruct | 48.2% | — |
| LMArena Coding | 1268 | — |
| BigCodeBench Complete | 58.2% | — |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Not comparable
GPT-4 Turbo: —, Magistral Small: —
| Benchmark | GPT-4 Turbo | Magistral Small |
|---|---|---|
| METR Time Horizons | 36.7% | — |
Reasoning GPT-4 Turbo leads
GPT-4 Turbo: 15.3 (#317), Magistral Small: 6.8 (#350)
| Benchmark | GPT-4 Turbo | Magistral Small |
|---|---|---|
| Chess Puzzles | 6% | 3% |
| DTBench | 61.6% | 61.3% |
| Epoch Capabilities Index | 127.25 | 133.19 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | 25.1% | — |
| Kagi LLM Benchmark | — | 6.3% |
| ARC-AGI-1 | — | 5% |
| CritPt | — | 0.3% |
| LMArena Hard Prompts | 1251 | — |
| LMCA | 9.8% | — |
| ForecastBench | 59.4 | — |
Math Magistral Small leads
GPT-4 Turbo: 9.0 (#322), Magistral Small: 26.2 (#261)
| Benchmark | GPT-4 Turbo | Magistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.7% | 30% |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| LMArena Math | 1272 | — |
| MATH Level 5 | 46.7% | — |
Knowledge Magistral Small leads
GPT-4 Turbo: 24.3 (#268), Magistral Small: 30.9 (#223)
| Benchmark | GPT-4 Turbo | Magistral Small |
|---|---|---|
| GPQA Diamond | 46.6% | 56.1% |
| Confabulations | 28.4% | — |
| LMArena Expert | 1223 | — |
| MMLU | 81.3% | — |
Multimodal Not comparable
GPT-4 Turbo: 30.6 (#110), Magistral Small: —
| Benchmark | GPT-4 Turbo | Magistral Small |
|---|---|---|
| LMArena Vision | 1090 | — |
Multilingual Not comparable
GPT-4 Turbo: 40.5 (#216), Magistral Small: —
| Benchmark | GPT-4 Turbo | Magistral Small |
|---|---|---|
| LMArena Non-English | 1245 | — |
| LMArena Chinese | 1242 | — |
| LMArena French | 1276 | — |
| LMArena German | 1259 | — |
| LMArena Japanese | 1194 | — |
| LMArena Korean | 1187 | — |
| LMArena Russian | 1259 | — |
| LMArena Spanish | 1260 | — |
Instruction Following Not comparable
GPT-4 Turbo: 65.8 (#216), Magistral Small: —
| Benchmark | GPT-4 Turbo | Magistral Small |
|---|---|---|
| LMArena Instruction Following | 1249 | — |
Long Context Not comparable
GPT-4 Turbo: 38.0 (#206), Magistral Small: —
| Benchmark | GPT-4 Turbo | Magistral Small |
|---|---|---|
| LMArena Longer Query | 1254 | — |
Writing & Preference Not comparable
GPT-4 Turbo: 47.7 (#206), Magistral Small: —
| Benchmark | GPT-4 Turbo | Magistral Small |
|---|---|---|
| LMArena Text | 1272 | — |
| LMArena Creative Writing | 1269 | — |
| LMArena Multi-Turn | 1267 | — |
Frequently asked questions
Is GPT-4 Turbo better than Magistral Small?
GPT-4 Turbo and Magistral Small score almost the same on the Noometry Index (30.5 vs 30.2), so choose on price, context window or the category you care about most.
Which is cheaper, GPT-4 Turbo or Magistral Small?
Magistral Small is cheaper. It lists at $0.50 per million input tokens and $1.50 per million output tokens; GPT-4 Turbo lists at $10 and $30.
Is GPT-4 Turbo or Magistral Small better for coding?
Magistral Small scores higher on coding benchmarks: 38.4 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do GPT-4 Turbo and Magistral Small share?
5 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Magistral Small has 10.