Model comparison
Gemini 3 Deep Think vs Magistral Medium
Magistral Medium has enough public results to be ranked (#227); Gemini 3 Deep Think does not yet, so treat this comparison as directional.
Last verified . 3 shared benchmarks.
Google
Mistral AISummary
- They share 3 benchmarks with published results for both. Gemini 3 Deep Think scores higher in 1 category and Magistral Medium in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3 Deep Think leads 70.2 to 8.6.
- The biggest single-benchmark swing is ARC-AGI-1: 96% for Gemini 3 Deep Think and 6.1% for Magistral Medium.
- Magistral Medium has downloadable open weights; the other is API-only.
Side by side
| Gemini 3 Deep Think | Magistral Medium | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 58.3 | 35.2 |
| Released | 2026-02-12 | 2025-03-17 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 16K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $5 |
| Results tracked | 3 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Gemini 3 Deep Think: —, Magistral Medium: 39.1 (#161)
| Benchmark | Gemini 3 Deep Think | Magistral Medium |
|---|---|---|
| SciCode | — | 39.2% |
| LMArena Coding | — | 1319 |
Reasoning Gemini 3 Deep Think leads
Gemini 3 Deep Think: 70.2 (#14), Magistral Medium: 8.6 (#348)
| Benchmark | Gemini 3 Deep Think | Magistral Medium |
|---|---|---|
| ARC-AGI-2 | 84.6% | 0% |
| ARC-AGI-1 | 96% | 6.1% |
| CritPt | 25.7% | 0.3% |
| Kagi LLM Benchmark | — | 16.2% |
| LMArena Hard Prompts | — | 1267 |
Math Not comparable
Gemini 3 Deep Think: —, Magistral Medium: 35.1 (#189)
| Benchmark | Gemini 3 Deep Think | Magistral Medium |
|---|---|---|
| LMArena Math | — | 1250 |
Knowledge Not comparable
Gemini 3 Deep Think: —, Magistral Medium: 33.5 (#202)
| Benchmark | Gemini 3 Deep Think | Magistral Medium |
|---|---|---|
| LMArena Expert | — | 1223 |
Multilingual Not comparable
Gemini 3 Deep Think: —, Magistral Medium: 39.6 (#224)
| Benchmark | Gemini 3 Deep Think | Magistral Medium |
|---|---|---|
| LMArena Non-English | — | 1232 |
| LMArena Chinese | — | 1227 |
| LMArena French | — | 1267 |
| LMArena German | — | 1248 |
| LMArena Japanese | — | 1175 |
| LMArena Korean | — | 1125 |
| LMArena Russian | — | 1224 |
| LMArena Spanish | — | 1271 |
Instruction Following Not comparable
Gemini 3 Deep Think: —, Magistral Medium: 66.0 (#211)
| Benchmark | Gemini 3 Deep Think | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | — | 1254 |
Long Context Not comparable
Gemini 3 Deep Think: —, Magistral Medium: 39.3 (#183)
| Benchmark | Gemini 3 Deep Think | Magistral Medium |
|---|---|---|
| LMArena Longer Query | — | 1295 |
Writing & Preference Not comparable
Gemini 3 Deep Think: —, Magistral Medium: 46.3 (#219)
| Benchmark | Gemini 3 Deep Think | Magistral Medium |
|---|---|---|
| LMArena Text | — | 1255 |
| LMArena Creative Writing | — | 1245 |
| LMArena Multi-Turn | — | 1275 |
Frequently asked questions
Is Gemini 3 Deep Think better than Magistral Medium?
Magistral Medium has enough public results to be ranked (#227); Gemini 3 Deep Think does not yet, so treat this comparison as directional.
How many benchmarks do Gemini 3 Deep Think and Magistral Medium share?
3 benchmarks have published results for both models. Gemini 3 Deep Think has 3 scored results on Noometry and Magistral Medium has 22.