Model comparison
GPT-5.5 Instant vs Magistral Medium
GPT-5.5 Instant is the stronger model overall, scoring 42.7 to 35.2 on the Noometry Index.
Last verified . 19 shared benchmarks.
Mistral AISummary
- They share 19 benchmarks with published results for both. GPT-5.5 Instant scores higher in 7 categories and Magistral Medium in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.5 Instant leads 24.9 to 8.6.
- The biggest single-benchmark swing is SciCode: 48.6% for GPT-5.5 Instant and 39.2% for Magistral Medium.
- Magistral Medium has downloadable open weights; the other is API-only.
Side by side
| GPT-5.5 Instant | Magistral Medium | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 42.7 | 35.2 |
| Released | 2026-05-05 | 2025-03-17 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 16K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $5 |
| Results tracked | 27 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.5 Instant leads
GPT-5.5 Instant: 44.3 (#74), Magistral Medium: 39.1 (#161)
| Benchmark | GPT-5.5 Instant | Magistral Medium |
|---|---|---|
| SciCode | 48.6% | 39.2% |
| LMArena Coding | 1433 | 1319 |
Reasoning GPT-5.5 Instant leads
GPT-5.5 Instant: 24.9 (#155), Magistral Medium: 8.6 (#348)
| Benchmark | GPT-5.5 Instant | Magistral Medium |
|---|---|---|
| CritPt | 0% | 0.3% |
| LMArena Hard Prompts | 1426 | 1267 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 16.2% |
| ARC-AGI-1 | — | 6.1% |
| Chess Puzzles | 12% | — |
| Epoch Capabilities Index | 142.52 | — |
Math Magistral Medium leads
GPT-5.5 Instant: 26.5 (#259), Magistral Medium: 35.1 (#189)
| Benchmark | GPT-5.5 Instant | Magistral Medium |
|---|---|---|
| LMArena Math | 1420 | 1250 |
| FrontierMath (Tiers 1-3) | 26.3% | — |
| FrontierMath Tier 4 | 2.4% | — |
| OTIS Mock AIME 2024-2025 | 68.1% | — |
Knowledge GPT-5.5 Instant leads
GPT-5.5 Instant: 48.9 (#74), Magistral Medium: 33.5 (#202)
| Benchmark | GPT-5.5 Instant | Magistral Medium |
|---|---|---|
| LMArena Expert | 1409 | 1223 |
| GPQA Diamond | 82.5% | — |
Multimodal Not comparable
GPT-5.5 Instant: 40.0 (#52), Magistral Medium: —
| Benchmark | GPT-5.5 Instant | Magistral Medium |
|---|---|---|
| LMArena Vision | 1250 | — |
| LMArena Document | 1403 | — |
Multilingual GPT-5.5 Instant leads
GPT-5.5 Instant: 52.8 (#80), Magistral Medium: 39.6 (#224)
| Benchmark | GPT-5.5 Instant | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1417 | 1232 |
| LMArena Chinese | 1456 | 1227 |
| LMArena French | 1428 | 1267 |
| LMArena German | 1411 | 1248 |
| LMArena Japanese | 1408 | 1175 |
| LMArena Korean | 1392 | 1125 |
| LMArena Russian | 1431 | 1224 |
| LMArena Spanish | 1429 | 1271 |
Instruction Following GPT-5.5 Instant leads
GPT-5.5 Instant: 74.2 (#100), Magistral Medium: 66.0 (#211)
| Benchmark | GPT-5.5 Instant | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1406 | 1254 |
Long Context GPT-5.5 Instant leads
GPT-5.5 Instant: 43.4 (#96), Magistral Medium: 39.3 (#183)
| Benchmark | GPT-5.5 Instant | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1422 | 1295 |
Writing & Preference GPT-5.5 Instant leads
GPT-5.5 Instant: 61.8 (#85), Magistral Medium: 46.3 (#219)
| Benchmark | GPT-5.5 Instant | Magistral Medium |
|---|---|---|
| LMArena Text | 1419 | 1255 |
| LMArena Creative Writing | 1419 | 1245 |
| LMArena Multi-Turn | 1433 | 1275 |
Frequently asked questions
Is GPT-5.5 Instant better than Magistral Medium?
GPT-5.5 Instant is the stronger model overall, scoring 42.7 to 35.2 on the Noometry Index.
Is GPT-5.5 Instant or Magistral Medium better for coding?
GPT-5.5 Instant scores higher on coding benchmarks: 44.3 versus 39.1 in the Noometry coding category.
How many benchmarks do GPT-5.5 Instant and Magistral Medium share?
19 benchmarks have published results for both models. GPT-5.5 Instant has 27 scored results on Noometry and Magistral Medium has 22.