Model comparison
GPT-5.3 Chat vs Mistral Medium
GPT-5.3 Chat is the stronger model overall, scoring 42.1 to 36.0 on the Noometry Index. Mistral Medium costs 1.6× less per token, which makes it the better buy when GPT-5.3 Chat's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
Mistral AISummary
- They share 17 benchmarks with published results for both. GPT-5.3 Chat scores higher in 5 categories and Mistral Medium in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.3 Chat leads 38.2 to 24.9.
- Mistral Medium is cheaper at $1.50 / $7.50 per million input/output tokens, against $1.75 / $14 for GPT-5.3 Chat.
- Mistral Medium accepts more context: 262K tokens versus 128K.
- Mistral Medium has downloadable open weights; the other is API-only.
Side by side
| GPT-5.3 Chat | Mistral Medium | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 42.1 | 36.0 |
| Released | 2026-03-03 | 2023-12-11 |
| Weights | Proprietary | Open |
| Context window | 128K | 262K |
| Max output | 16K | 262K |
| Input $ / M tokens | $1.75 | $1.50 |
| Output $ / M tokens | $14 | $7.50 |
| Results tracked | 18 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.3 Chat leads
GPT-5.3 Chat: 40.8 (#124), Mistral Medium: 33.8 (#241)
| Benchmark | GPT-5.3 Chat | Mistral Medium |
|---|---|---|
| LMArena Coding | 1408 | 1434 |
| FrontierCode | — | 8% |
| SciCode | — | 40.2% |
| WeirdML | — | 43.7% |
| ALE-Bench | — | 763.98 |
Agentic & Tool Use Not comparable
GPT-5.3 Chat: —, Mistral Medium: 28.1 (#84)
| Benchmark | GPT-5.3 Chat | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |
Reasoning GPT-5.3 Chat leads
GPT-5.3 Chat: 27.3 (#105), Mistral Medium: 23.3 (#165)
| Benchmark | GPT-5.3 Chat | Mistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1399 | 1426 |
| Kagi LLM Benchmark | — | 50% |
| CritPt | — | 0% |
| DTBench | — | 75.5% |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |
Math GPT-5.3 Chat leads
GPT-5.3 Chat: 35.4 (#146), Mistral Medium: 27.2 (#238)
| Benchmark | GPT-5.3 Chat | Mistral Medium |
|---|---|---|
| LMArena Math | 1389 | 1409 |
| OTIS Mock AIME 2024-2025 | — | 32.2% |
| ProofBench | — | 9% |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge GPT-5.3 Chat leads
GPT-5.3 Chat: 38.2 (#137), Mistral Medium: 24.9 (#260)
| Benchmark | GPT-5.3 Chat | Mistral Medium |
|---|---|---|
| LMArena Expert | 1397 | 1408 |
| GPQA Diamond | — | 59.5% |
| Humanity's Last Exam | — | 4.5% |
| Vectara Hallucination Rate | — | 22.7% |
Multimodal Not comparable
GPT-5.3 Chat: —, Mistral Medium: 34.6 (#82)
| Benchmark | GPT-5.3 Chat | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |
Multilingual Mistral Medium leads
GPT-5.3 Chat: 50.5 (#119), Mistral Medium: 52.3 (#86)
| Benchmark | GPT-5.3 Chat | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1383 | 1408 |
| LMArena Chinese | 1433 | 1448 |
| LMArena French | 1398 | 1460 |
| LMArena German | 1384 | 1433 |
| LMArena Japanese | 1351 | 1378 |
| LMArena Korean | 1347 | 1382 |
| LMArena Russian | 1400 | 1411 |
| LMArena Spanish | 1371 | 1433 |
Instruction Following Too close to call
GPT-5.3 Chat: 73.0 (#124), Mistral Medium: 73.9 (#111)
| Benchmark | GPT-5.3 Chat | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1378 | 1398 |
Long Context Too close to call
GPT-5.3 Chat: 42.6 (#115), Mistral Medium: 42.9 (#108)
| Benchmark | GPT-5.3 Chat | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1396 | 1406 |
Writing & Preference GPT-5.3 Chat leads
GPT-5.3 Chat: 63.3 (#65), Mistral Medium: 60.2 (#97)
| Benchmark | GPT-5.3 Chat | Mistral Medium |
|---|---|---|
| LMArena Text | 1389 | 1424 |
| LMArena Creative Writing | 1356 | 1391 |
| LMArena Multi-Turn | 1413 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
| EQ-Bench Creative Writing | 1690 | — |
Frequently asked questions
Is GPT-5.3 Chat better than Mistral Medium?
GPT-5.3 Chat is the stronger model overall, scoring 42.1 to 36.0 on the Noometry Index. Mistral Medium costs 1.6× less per token, which makes it the better buy when GPT-5.3 Chat's lead doesn't matter for your workload.
Which is cheaper, GPT-5.3 Chat or Mistral Medium?
Mistral Medium is cheaper. It lists at $1.50 per million input tokens and $7.50 per million output tokens; GPT-5.3 Chat lists at $1.75 and $14.
Is GPT-5.3 Chat or Mistral Medium better for coding?
GPT-5.3 Chat scores higher on coding benchmarks: 40.8 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
Mistral Medium does, with 262K tokens against 128K.
How many benchmarks do GPT-5.3 Chat and Mistral Medium share?
17 benchmarks have published results for both models. GPT-5.3 Chat has 18 scored results on Noometry and Mistral Medium has 36.