Model comparison
GPT-6.1 Sol vs Magistral Medium
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 35.2 on the Noometry Index.
Last verified . 16 shared benchmarks.
Mistral AISummary
- They share 16 benchmarks with published results for both. GPT-6.1 Sol scores higher in 8 categories and Magistral Medium in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6.1 Sol leads 81.9 to 8.6.
- The biggest single-benchmark swing is ARC-AGI-2: 94.2% for GPT-6.1 Sol and 0% for Magistral Medium.
- Magistral Medium is cheaper at $2 / $5 per million input/output tokens, against $2 / $10 for GPT-6.1 Sol.
- GPT-6.1 Sol accepts more context: 1.05M tokens versus 262K.
- Magistral Medium has downloadable open weights; the other is API-only.
Side by side
| GPT-6.1 Sol | Magistral Medium | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 65.6 | 35.2 |
| Released | 2026-09-29 | 2025-03-17 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 128K | 16K |
| Input $ / M tokens | $2 | $2 |
| Output $ / M tokens | $10 | $5 |
| Results tracked | 34 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6.1 Sol leads
GPT-6.1 Sol: 63.2 (#8), Magistral Medium: 39.1 (#161)
| Benchmark | GPT-6.1 Sol | Magistral Medium |
|---|---|---|
| SciCode | 55.8% | 39.2% |
| LMArena Coding | 1487 | 1319 |
| DeepSWE | 75.2% | — |
| FrontierCode | 50.2% | — |
| LMArena WebDev | 1755 | — |
Agentic & Tool Use Not comparable
GPT-6.1 Sol: 39.6 (#26), Magistral Medium: —
| Benchmark | GPT-6.1 Sol | Magistral Medium |
|---|---|---|
| APEX-Agents | 60% | — |
| GDP.pdf | 32% | — |
Reasoning GPT-6.1 Sol leads
GPT-6.1 Sol: 81.9 (#2), Magistral Medium: 8.6 (#348)
| Benchmark | GPT-6.1 Sol | Magistral Medium |
|---|---|---|
| ARC-AGI-2 | 94.2% | 0% |
| ARC-AGI-1 | 98.5% | 6.1% |
| CritPt | 31.7% | 0.3% |
| LMArena Hard Prompts | 1466 | 1267 |
| Kagi LLM Benchmark | — | 16.2% |
| NYT Connections (extended) | 95.5% | — |
| Chess Puzzles | 61% | — |
| EBR-Bench | 54.3% | — |
| Mystery Game Puzzles | 80% | — |
| Epoch Capabilities Index | 166.09 | — |
Math GPT-6.1 Sol leads
GPT-6.1 Sol: 93.7 (#1), Magistral Medium: 35.1 (#189)
| Benchmark | GPT-6.1 Sol | Magistral Medium |
|---|---|---|
| LMArena Math | 1464 | 1250 |
| FrontierMath (Tiers 1-3) | 93.7% | — |
| FrontierMath Tier 4 | 100% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| ProofBench | 99% | — |
Knowledge GPT-6.1 Sol leads
GPT-6.1 Sol: 71.8 (#4), Magistral Medium: 33.5 (#202)
| Benchmark | GPT-6.1 Sol | Magistral Medium |
|---|---|---|
| LMArena Expert | 1502 | 1223 |
| GPQA Diamond | 95.4% | — |
| SimpleQA Verified | 73.9% | — |
Multimodal Not comparable
GPT-6.1 Sol: 52.7 (#5), Magistral Medium: —
| Benchmark | GPT-6.1 Sol | Magistral Medium |
|---|---|---|
| LMArena Vision | 1288 | — |
| Furniture Assembly | 80% | — |
Multilingual GPT-6.1 Sol leads
GPT-6.1 Sol: 54.3 (#46), Magistral Medium: 39.6 (#224)
| Benchmark | GPT-6.1 Sol | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1438 | 1232 |
| LMArena Chinese | 1477 | 1227 |
| LMArena Russian | 1455 | 1224 |
| LMArena French | — | 1267 |
| LMArena German | — | 1248 |
| LMArena Japanese | — | 1175 |
| LMArena Korean | — | 1125 |
| LMArena Spanish | — | 1271 |
Instruction Following GPT-6.1 Sol leads
GPT-6.1 Sol: 77.0 (#29), Magistral Medium: 66.0 (#211)
| Benchmark | GPT-6.1 Sol | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1468 | 1254 |
Long Context GPT-6.1 Sol leads
GPT-6.1 Sol: 44.9 (#54), Magistral Medium: 39.3 (#183)
| Benchmark | GPT-6.1 Sol | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1465 | 1295 |
Writing & Preference GPT-6.1 Sol leads
GPT-6.1 Sol: 63.6 (#63), Magistral Medium: 46.3 (#219)
| Benchmark | GPT-6.1 Sol | Magistral Medium |
|---|---|---|
| LMArena Text | 1447 | 1255 |
| LMArena Creative Writing | 1432 | 1245 |
| LMArena Multi-Turn | 1449 | 1275 |
Frequently asked questions
Is GPT-6.1 Sol better than Magistral Medium?
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 35.2 on the Noometry Index.
Which is cheaper, GPT-6.1 Sol or Magistral Medium?
Magistral Medium is cheaper. It lists at $2 per million input tokens and $5 per million output tokens; GPT-6.1 Sol lists at $2 and $10.
Is GPT-6.1 Sol or Magistral Medium better for coding?
GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 39.1 in the Noometry coding category.
Which has the bigger context window?
GPT-6.1 Sol does, with 1.05M tokens against 262K.
How many benchmarks do GPT-6.1 Sol and Magistral Medium share?
16 benchmarks have published results for both models. GPT-6.1 Sol has 34 scored results on Noometry and Magistral Medium has 22.