Model comparison
DeepSeek-V3.1-Terminus vs Mistral Medium
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 36.0 on the Noometry Index.
Last verified . 16 shared benchmarks.
DeepSeek
Mistral AISummary
- They share 16 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 6 categories and Mistral Medium in 1 category; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek-V3.1-Terminus leads 35.7 to 27.2.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 57.4% for DeepSeek-V3.1-Terminus and 50% for Mistral Medium.
- DeepSeek-V3.1-Terminus is cheaper at $0.30 / $1 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- Mistral Medium accepts more context: 262K tokens versus 164K.
Side by side
| DeepSeek-V3.1-Terminus | Mistral Medium | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 42.6 | 36.0 |
| Released | 2025-09-22 | 2023-12-11 |
| Weights | Open | Open |
| Context window | 164K | 262K |
| Max output | 66K | 262K |
| Input $ / M tokens | $0.30 | $1.50 |
| Output $ / M tokens | $1 | $7.50 |
| Results tracked | 16 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 41.5 (#114), Mistral Medium: 33.8 (#241)
| Benchmark | DeepSeek-V3.1-Terminus | Mistral Medium |
|---|---|---|
| SciCode | 40.6% | 40.2% |
| LMArena Coding | 1426 | 1434 |
| ALE-Bench | 745.17 | 763.98 |
| FrontierCode | — | 8% |
| WeirdML | — | 43.7% |
Agentic & Tool Use Not comparable
DeepSeek-V3.1-Terminus: —, Mistral Medium: 28.1 (#84)
| Benchmark | DeepSeek-V3.1-Terminus | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 25.7 (#126), Mistral Medium: 23.3 (#165)
| Benchmark | DeepSeek-V3.1-Terminus | Mistral Medium |
|---|---|---|
| Kagi LLM Benchmark | 57.4% | 50% |
| CritPt | 1.7% | 0% |
| LMArena Hard Prompts | 1427 | 1426 |
| DTBench | 81.3% | 75.5% |
| LMCA | 28.6% | 26.1% |
| Surface Evolver Bench | — | 26.9% |
Math DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 35.7 (#138), Mistral Medium: 27.2 (#238)
| Benchmark | DeepSeek-V3.1-Terminus | Mistral Medium |
|---|---|---|
| LMArena Math | 1402 | 1409 |
| OTIS Mock AIME 2024-2025 | — | 32.2% |
| ProofBench | — | 9% |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Mistral Medium: 24.9 (#260)
| Benchmark | DeepSeek-V3.1-Terminus | Mistral Medium |
|---|---|---|
| GPQA Diamond | — | 59.5% |
| Humanity's Last Exam | — | 4.5% |
| Vectara Hallucination Rate | — | 22.7% |
| LMArena Expert | — | 1408 |
Multimodal Not comparable
DeepSeek-V3.1-Terminus: —, Mistral Medium: 34.6 (#82)
| Benchmark | DeepSeek-V3.1-Terminus | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |
Multilingual Too close to call
DeepSeek-V3.1-Terminus: 52.3 (#87), Mistral Medium: 52.3 (#86)
| Benchmark | DeepSeek-V3.1-Terminus | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1407 | 1408 |
| LMArena Russian | 1434 | 1411 |
| LMArena Chinese | — | 1448 |
| LMArena French | — | 1460 |
| LMArena German | — | 1433 |
| LMArena Japanese | — | 1378 |
| LMArena Korean | — | 1382 |
| LMArena Spanish | — | 1433 |
Instruction Following Too close to call
DeepSeek-V3.1-Terminus: 74.4 (#96), Mistral Medium: 73.9 (#111)
| Benchmark | DeepSeek-V3.1-Terminus | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1406 | 1398 |
Long Context Too close to call
DeepSeek-V3.1-Terminus: 43.5 (#88), Mistral Medium: 42.9 (#108)
| Benchmark | DeepSeek-V3.1-Terminus | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1426 | 1406 |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.3 (#87), Mistral Medium: 60.2 (#97)
| Benchmark | DeepSeek-V3.1-Terminus | Mistral Medium |
|---|---|---|
| LMArena Text | 1420 | 1424 |
| LMArena Creative Writing | 1404 | 1391 |
| LMArena Multi-Turn | 1411 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Mistral Medium?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 36.0 on the Noometry Index.
Which is cheaper, DeepSeek-V3.1-Terminus or Mistral Medium?
DeepSeek-V3.1-Terminus is cheaper. It lists at $0.30 per million input tokens and $1 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is DeepSeek-V3.1-Terminus or Mistral Medium better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 41.5 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
Mistral Medium does, with 262K tokens against 164K.
How many benchmarks do DeepSeek-V3.1-Terminus and Mistral Medium share?
16 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Mistral Medium has 36.