Model comparison
Devstral Medium vs GPT-5.2 Pro
GPT-5.2 Pro has enough public results to be ranked (#39); Devstral Medium does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Mistral AISummary
- The widest gap is in reasoning, where GPT-5.2 Pro leads 51.5 to 21.1.
- Devstral Medium is cheaper at $0.40 / $2 per million input/output tokens, against $21 / $168 for GPT-5.2 Pro.
- GPT-5.2 Pro accepts more context: 400K tokens versus 262K.
- Devstral Medium has downloadable open weights; the other is API-only.
Side by side
| Devstral Medium | GPT-5.2 Pro | |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Noometry Index | 30.1 | 52.3 |
| Released | 2025-07-10 | 2025-12-11 |
| Weights | Open | Proprietary |
| Context window | 262K | 400K |
| Max output | 262K | 128K |
| Input $ / M tokens | $0.40 | $21 |
| Output $ / M tokens | $2 | $168 |
| Results tracked | 2 | 8 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Devstral Medium: 24.3, GPT-5.2 Pro: —
| Benchmark | Devstral Medium | GPT-5.2 Pro |
|---|---|---|
| LMArena WebDev | 1076 | — |
Reasoning GPT-5.2 Pro leads
Devstral Medium: 21.1, GPT-5.2 Pro: 51.5 (#33)
| Benchmark | Devstral Medium | GPT-5.2 Pro |
|---|---|---|
| ARC-AGI-2 | — | 54.2% |
| SimpleBench | — | 57.4% |
| Kagi LLM Benchmark | 37.7% | — |
| NYT Connections (extended) | — | 79.3% |
| ARC-AGI-1 | — | 90.5% |
| Epoch Capabilities Index | — | 155.4 |
Math Not comparable
Devstral Medium: —, GPT-5.2 Pro: 65.3 (#29)
| Benchmark | Devstral Medium | GPT-5.2 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 74% |
| FrontierMath Tier 4 | — | 46% |
| FrontierMath Tier 4 (v1) | — | 31.3% |
Frequently asked questions
Is Devstral Medium better than GPT-5.2 Pro?
GPT-5.2 Pro has enough public results to be ranked (#39); Devstral Medium does not yet, so treat this comparison as directional.
Which is cheaper, Devstral Medium or GPT-5.2 Pro?
Devstral Medium is cheaper. It lists at $0.40 per million input tokens and $2 per million output tokens; GPT-5.2 Pro lists at $21 and $168.
Which has the bigger context window?
GPT-5.2 Pro does, with 400K tokens against 262K.
How many benchmarks do Devstral Medium and GPT-5.2 Pro share?
0 benchmarks have published results for both models. Devstral Medium has 2 scored results on Noometry and GPT-5.2 Pro has 8.