Model comparison
Grok 4.7 vs Mistral Large 3
Grok 4.7 is the stronger model overall, scoring 53.1 to 39.1 on the Noometry Index. Mistral Large 3 costs 8.0× less per token, which makes it the better buy when Grok 4.7's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
Mistral AISummary
- They share 18 benchmarks with published results for both. Grok 4.7 scores higher in 6 categories and Mistral Large 3 in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.7 leads 49.1 to 15.2.
- The biggest single-benchmark swing is NYT Connections (extended): 76.8% for Grok 4.7 and 7.5% for Mistral Large 3.
- Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $2 / $6 for Grok 4.7.
- Grok 4.7 accepts more context: 500K tokens versus 262K.
- Mistral Large 3 has downloadable open weights; the other is API-only.
Side by side
| Grok 4.7 | Mistral Large 3 | |
|---|---|---|
| Provider | xAI | Mistral AI |
| Noometry Index | 53.1 | 39.1 |
| Released | 2026-09-21 | 2025-12-02 |
| Weights | Proprietary | Open |
| Context window | 500K | 262K |
| Max output | 500K | 8K |
| Input $ / M tokens | $2 | $0.25 |
| Output $ / M tokens | $6 | $0.75 |
| Results tracked | 39 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.7 leads
Grok 4.7: 58.0 (#18), Mistral Large 3: 34.4 (#237)
| Benchmark | Grok 4.7 | Mistral Large 3 |
|---|---|---|
| LMArena WebDev | 1639 | 1230 |
| LMArena Coding | 1427 | 1448 |
| FrontierCode | 47.6% | — |
| CursorBench | 46.3% | — |
| FrontierSWE | 29.5% | — |
| SciCode | 57.8% | — |
Agentic & Tool Use Not comparable
Grok 4.7: 36.7 (#37), Mistral Large 3: —
| Benchmark | Grok 4.7 | Mistral Large 3 |
|---|---|---|
| APEX-Agents | 54.6% | — |
| GDP.pdf | 22.8% | — |
| Vending-Bench 2 | 10,537 | — |
Reasoning Grok 4.7 leads
Grok 4.7: 49.1 (#40), Mistral Large 3: 15.2 (#319)
| Benchmark | Grok 4.7 | Mistral Large 3 |
|---|---|---|
| NYT Connections (extended) | 76.8% | 7.5% |
| LMArena Hard Prompts | 1413 | 1429 |
| Kagi LLM Benchmark | — | 50.9% |
| CritPt | 18% | — |
| Chess Puzzles | 38% | — |
| Thematic Generalization | — | 23% |
| Mystery Game Puzzles | 29% | — |
| DTBench | 96% | — |
| LMCA | 49.4% | — |
| Epoch Capabilities Index | 153.53 | — |
Math Grok 4.7 leads
Grok 4.7: 57.8 (#39), Mistral Large 3: 38.7 (#129)
| Benchmark | Grok 4.7 | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1407 | 1414 |
| FrontierMath (Tiers 1-3) | 53% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 98.1% | — |
| ProofBench | 34% | — |
Knowledge Grok 4.7 leads
Grok 4.7: 62.8 (#22), Mistral Large 3: 36.0 (#177)
| Benchmark | Grok 4.7 | Mistral Large 3 |
|---|---|---|
| LMArena Expert | 1422 | 1421 |
| GPQA Diamond | 92.7% | — |
| SimpleQA Verified | 56% | — |
| Vectara Hallucination Rate | — | 14.5% |
Multimodal Mistral Large 3 leads
Grok 4.7: 35.5 (#87), Mistral Large 3: 38.2 (#66)
| Benchmark | Grok 4.7 | Mistral Large 3 |
|---|---|---|
| LMArena Vision | 1228 | 1221 |
| Blueprint-Bench 2 | 32.5% | — |
| Furniture Assembly | 20.8% | — |
Multilingual Mistral Large 3 leads
Grok 4.7: 50.8 (#116), Mistral Large 3: 52.5 (#84)
| Benchmark | Grok 4.7 | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1389 | 1413 |
| LMArena Chinese | 1455 | 1447 |
| LMArena French | 1455 | 1455 |
| LMArena Russian | 1397 | 1411 |
| LMArena Spanish | 1400 | 1440 |
| LMArena German | — | 1437 |
| LMArena Japanese | — | 1394 |
| LMArena Korean | — | 1384 |
Instruction Following Too close to call
Grok 4.7: 74.1 (#105), Mistral Large 3: 74.0 (#108)
| Benchmark | Grok 4.7 | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1404 | 1403 |
Long Context Too close to call
Grok 4.7: 43.1 (#104), Mistral Large 3: 43.1 (#105)
| Benchmark | Grok 4.7 | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1413 | 1413 |
Writing & Preference Grok 4.7 leads
Grok 4.7: 70.0 (#24), Mistral Large 3: 60.0 (#101)
| Benchmark | Grok 4.7 | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1399 | 1428 |
| LMArena Creative Writing | 1391 | 1386 |
| EQ-Bench Creative Writing | 2007 | 1412 |
| LMArena Multi-Turn | 1393 | 1429 |
Frequently asked questions
Is Grok 4.7 better than Mistral Large 3?
Grok 4.7 is the stronger model overall, scoring 53.1 to 39.1 on the Noometry Index. Mistral Large 3 costs 8.0× less per token, which makes it the better buy when Grok 4.7's lead doesn't matter for your workload.
Which is cheaper, Grok 4.7 or Mistral Large 3?
Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Grok 4.7 lists at $2 and $6.
Is Grok 4.7 or Mistral Large 3 better for coding?
Grok 4.7 scores higher on coding benchmarks: 58.0 versus 34.4 in the Noometry coding category.
Which has the bigger context window?
Grok 4.7 does, with 500K tokens against 262K.
How many benchmarks do Grok 4.7 and Mistral Large 3 share?
18 benchmarks have published results for both models. Grok 4.7 has 39 scored results on Noometry and Mistral Large 3 has 24.