Model comparison
Grok 4.6 vs Mistral Medium
Grok 4.6 is the stronger model overall, scoring 56.9 to 36.3 on the Noometry Index.
Last verified . 28 shared benchmarks.
Mistral AISummary
- They share 28 benchmarks with published results for both. Grok 4.6 scores higher in 10 categories and Mistral Medium in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok 4.6 leads 67.0 to 28.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 99.2% for Grok 4.6 and 32.2% for Mistral Medium.
- Both cost about the same: $2 input and $6 output per million tokens.
- Grok 4.6 accepts more context: 500K tokens versus 262K.
- Mistral Medium has downloadable open weights; the other is API-only.
Side by side
| Grok 4.6 | Mistral Medium | |
|---|---|---|
| Provider | xAI | Mistral AI |
| Noometry Index | 56.9 | 36.3 |
| Released | 2026-08-12 | 2023-12-11 |
| Weights | Proprietary | Open |
| Context window | 500K | 262K |
| Max output | 500K | 262K |
| Input $ / M tokens | $2 | $1.50 |
| Output $ / M tokens | $6 | $7.50 |
| Results tracked | 49 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.6 leads
Grok 4.6: 58.5 (#16), Mistral Medium: 34.2 (#243)
| Benchmark | Grok 4.6 | Mistral Medium |
|---|---|---|
| FrontierCode | 48% | 8% |
| SciCode | 56.5% | 40.2% |
| WeirdML | 67.3% | 43.7% |
| LMArena Coding | 1465 | 1434 |
| ALE-Bench | 1,508 | 763.98 |
| DeepSWE | 67.5% | — |
| CursorBench | 41.4% | — |
| LMArena WebDev | 1617 | — |
| FrontierSWE | 25.3% | — |
Agentic & Tool Use Grok 4.6 leads
Grok 4.6: 39.4 (#27), Mistral Medium: 28.3 (#90)
| Benchmark | Grok 4.6 | Mistral Medium |
|---|---|---|
| APEX-Agents | 65.3% | — |
| Berkeley Function Calling Leaderboard | — | 37.7% |
| GDP.pdf | 17.2% | — |
| Vending-Bench 2 | 9,047 | — |
Reasoning Grok 4.6 leads
Grok 4.6: 61.4 (#20), Mistral Medium: 24.0 (#167)
| Benchmark | Grok 4.6 | Mistral Medium |
|---|---|---|
| CritPt | 19.7% | 0% |
| LMArena Hard Prompts | 1447 | 1426 |
| DTBench | 97.3% | 75.5% |
| LMCA | 48.5% | 26.1% |
| ARC-AGI-2 | 67.1% | — |
| SimpleBench | 75.9% | — |
| Kagi LLM Benchmark | — | 50% |
| NYT Connections (extended) | 80% | — |
| ARC-AGI-1 | 87.5% | — |
| Chess Puzzles | 40% | — |
| EBR-Bench | 30.5% | — |
| Mystery Game Puzzles | 34% | — |
| Surface Evolver Bench | — | 26.9% |
| Epoch Capabilities Index | 156.44 | — |
Math Grok 4.6 leads
Grok 4.6: 67.0 (#24), Mistral Medium: 28.1 (#245)
| Benchmark | Grok 4.6 | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 99.2% | 32.2% |
| ProofBench | 51% | 9% |
| LMArena Math | 1423 | 1408 |
| FrontierMath (Tiers 1-3) | 66% | — |
| FrontierMath Tier 4 | 31.7% | — |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Grok 4.6 leads
Grok 4.6: 63.3 (#20), Mistral Medium: 25.0 (#265)
| Benchmark | Grok 4.6 | Mistral Medium |
|---|---|---|
| GPQA Diamond | 94% | 59.5% |
| LMArena Expert | 1467 | 1408 |
| Humanity's Last Exam | — | 4.5% |
| SimpleQA Verified | 49.3% | — |
| Vectara Hallucination Rate | — | 22.7% |
Multimodal Grok 4.6 leads
Grok 4.6: 43.6 (#23), Mistral Medium: 35.3 (#88)
| Benchmark | Grok 4.6 | Mistral Medium |
|---|---|---|
| LMArena Vision | 1263 | 1172 |
| Blueprint-Bench 2 | 33.2% | — |
| Furniture Assembly | 40% | — |
| LMArena Document | 1452 | — |
Multilingual Too close to call
Grok 4.6: 53.0 (#74), Mistral Medium: 52.1 (#91)
| Benchmark | Grok 4.6 | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1420 | 1408 |
| LMArena Chinese | 1480 | 1447 |
| LMArena French | 1461 | 1459 |
| LMArena German | 1431 | 1432 |
| LMArena Japanese | 1376 | 1378 |
| LMArena Korean | 1397 | 1380 |
| LMArena Russian | 1422 | 1411 |
| LMArena Spanish | 1404 | 1433 |
Instruction Following Grok 4.6 leads
Grok 4.6: 75.4 (#63), Mistral Medium: 73.7 (#116)
| Benchmark | Grok 4.6 | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1431 | 1398 |
Long Context Grok 4.6 leads
Grok 4.6: 44.5 (#66), Mistral Medium: 42.9 (#114)
| Benchmark | Grok 4.6 | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1454 | 1406 |
Writing & Preference Grok 4.6 leads
Grok 4.6: 62.3 (#80), Mistral Medium: 60.0 (#103)
| Benchmark | Grok 4.6 | Mistral Medium |
|---|---|---|
| LMArena Text | 1428 | 1424 |
| LMArena Creative Writing | 1428 | 1391 |
| LMArena Multi-Turn | 1425 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
Frequently asked questions
Is Grok 4.6 better than Mistral Medium?
Grok 4.6 is the stronger model overall, scoring 56.9 to 36.3 on the Noometry Index.
Which is cheaper, Grok 4.6 or Mistral Medium?
Mistral Medium is cheaper. It lists at $1.50 per million input tokens and $7.50 per million output tokens; Grok 4.6 lists at $2 and $6.
Is Grok 4.6 or Mistral Medium better for coding?
Grok 4.6 scores higher on coding benchmarks: 58.5 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
Grok 4.6 does, with 500K tokens against 262K.
How many benchmarks do Grok 4.6 and Mistral Medium share?
28 benchmarks have published results for both models. Grok 4.6 has 49 scored results on Noometry and Mistral Medium has 36.