Model comparison
Gemini 2.5 Flash vs Magistral Medium
Gemini 2.5 Flash is the stronger model overall, scoring 39.0 to 34.8 on the Noometry Index.
Last verified . 21 shared benchmarks.
Google
Mistral AISummary
- They share 21 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 7 categories and Magistral Medium in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Gemini 2.5 Flash leads 52.5 to 39.8.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 56.8% for Gemini 2.5 Flash and 16.2% for Magistral Medium.
- Gemini 2.5 Flash is cheaper at $0.30 / $2.50 per million input/output tokens, against $2 / $5 for Magistral Medium.
- Gemini 2.5 Flash accepts more context: 1.05M tokens versus 128K.
- Magistral Medium has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.5 Flash | Magistral Medium | |
|---|---|---|
| Provider | Mistral AI | |
| Noometry Index | 39.0 | 34.8 |
| Released | 2025-04-17 | 2025-03-17 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 128K |
| Max output | 66K | 16K |
| Input $ / M tokens | $0.30 | $2 |
| Output $ / M tokens | $2.50 | $5 |
| Results tracked | 54 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Magistral Medium leads
Gemini 2.5 Flash: 35.5 (#210), Magistral Medium: 38.6 (#161)
| Benchmark | Gemini 2.5 Flash | Magistral Medium |
|---|---|---|
| LMArena Coding | 1424 | 1319 |
| SWE-bench Verified (bash only) | 28.7% | — |
| Aider Polyglot | 55.1% | — |
| SciCode | — | 39.2% |
| WeirdML | 41.9% | — |
| ALE-Bench | 661.88 | — |
Agentic & Tool Use Not comparable
Gemini 2.5 Flash: 30.6 (#67), Magistral Medium: —
| Benchmark | Gemini 2.5 Flash | Magistral Medium |
|---|---|---|
| Terminal-Bench | 17.1% | — |
| Berkeley Function Calling Leaderboard | 56.2% | — |
| TheAgentCompany | 41.1% | — |
| BALROG | 33.5% | — |
| Vending-Bench 2 | 548.84 | — |
Reasoning Gemini 2.5 Flash leads
Gemini 2.5 Flash: 18.2 (#271), Magistral Medium: 8.7 (#342)
| Benchmark | Gemini 2.5 Flash | Magistral Medium |
|---|---|---|
| ARC-AGI-2 | 2.5% | 0% |
| Kagi LLM Benchmark | 56.8% | 16.2% |
| ARC-AGI-1 | 33.3% | 6.1% |
| CritPt | 1.1% | 0.3% |
| LMArena Hard Prompts | 1422 | 1267 |
| SimpleBench | 41.2% | — |
| EnigmaEval | 2.7% | — |
| DTBench | 76.5% | — |
| LMCA | 27.5% | — |
| Epoch Capabilities Index | 143.04 | — |
| ForecastBench | 60.6 | — |
Math Gemini 2.5 Flash leads
Gemini 2.5 Flash: 38.1 (#87), Magistral Medium: 32.4 (#187)
| Benchmark | Gemini 2.5 Flash | Magistral Medium |
|---|---|---|
| LMArena Math | 1415 | 1249 |
| OTIS Mock AIME 2024-2025 | 73.1% | — |
| Omni-MATH | 38.5% | — |
| FrontierMath (Feb 2025 set) | 4.8% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Gemini 2.5 Flash leads
Gemini 2.5 Flash: 36.1 (#162), Magistral Medium: 32.9 (#199)
| Benchmark | Gemini 2.5 Flash | Magistral Medium |
|---|---|---|
| LMArena Expert | 1426 | 1222 |
| Humanity's Last Exam | 12.1% | — |
| MMLU-Pro | 63.9% | — |
| Confabulations | 16.8% | — |
| Vectara Hallucination Rate | 7.8% | — |
| GPQA (HELM) | 39% | — |
Multimodal Not comparable
Gemini 2.5 Flash: 41.2 (#31), Magistral Medium: —
| Benchmark | Gemini 2.5 Flash | Magistral Medium |
|---|---|---|
| LMArena Vision | 1254 | — |
| GeoBench | 76% | — |
| VPCT | 46.2% | — |
| SpatialViz-Bench | 36.9% | — |
Multilingual Gemini 2.5 Flash leads
Gemini 2.5 Flash: 52.5 (#83), Magistral Medium: 39.8 (#219)
| Benchmark | Gemini 2.5 Flash | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1410 | 1232 |
| LMArena Chinese | 1450 | 1225 |
| LMArena French | 1433 | 1268 |
| LMArena German | 1419 | 1248 |
| LMArena Japanese | 1403 | 1176 |
| LMArena Korean | 1385 | 1125 |
| LMArena Russian | 1415 | 1224 |
| LMArena Spanish | 1421 | 1269 |
Instruction Following Gemini 2.5 Flash leads
Gemini 2.5 Flash: 75.9 (#50), Magistral Medium: 66.2 (#207)
| Benchmark | Gemini 2.5 Flash | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1405 | 1254 |
| IFEval | 89.8% | — |
Long Context Gemini 2.5 Flash leads
Gemini 2.5 Flash: 47.5 (#16), Magistral Medium: 39.3 (#178)
| Benchmark | Gemini 2.5 Flash | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1419 | 1295 |
| Fiction.LiveBench | 77.8% | — |
Writing & Preference Gemini 2.5 Flash leads
Gemini 2.5 Flash: 54.0 (#153), Magistral Medium: 46.5 (#214)
| Benchmark | Gemini 2.5 Flash | Magistral Medium |
|---|---|---|
| LMArena Text | 1417 | 1255 |
| LMArena Creative Writing | 1400 | 1245 |
| LMArena Multi-Turn | 1408 | 1275 |
| Short-Story Creative Writing | 76.5% | — |
| EQ-Bench Creative Writing | 1137 | — |
| WildBench | 81.7% | — |
Frequently asked questions
Is Gemini 2.5 Flash better than Magistral Medium?
Gemini 2.5 Flash is the stronger model overall, scoring 39.0 to 34.8 on the Noometry Index.
Which is cheaper, Gemini 2.5 Flash or Magistral Medium?
Gemini 2.5 Flash is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; Magistral Medium lists at $2 and $5.
Is Gemini 2.5 Flash or Magistral Medium better for coding?
Magistral Medium scores higher on coding benchmarks: 38.6 versus 35.5 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Flash does, with 1.05M tokens against 128K.
How many benchmarks do Gemini 2.5 Flash and Magistral Medium share?
21 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and Magistral Medium has 22.