Model comparison
Grok 4.6 vs Ministral 8B
Grok 4.6 is the stronger model overall, scoring 56.9 to 28.2 on the Noometry Index. Ministral 8B costs 20× less per token, which makes it the better buy when Grok 4.6's lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
Mistral AISummary
- They share 14 benchmarks with published results for both. Grok 4.6 scores higher in 9 categories and Ministral 8B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 4.6 leads 63.3 to 12.6.
- The biggest single-benchmark swing is GPQA Diamond: 94% for Grok 4.6 and 27.1% for Ministral 8B.
- Ministral 8B is cheaper at $0.15 / $0.15 per million input/output tokens, against $2 / $6 for Grok 4.6.
- Grok 4.6 accepts more context: 500K tokens versus 262K.
- Ministral 8B has downloadable open weights; the other is API-only.
Side by side
| Grok 4.6 | Ministral 8B | |
|---|---|---|
| Provider | xAI | Mistral AI |
| Noometry Index | 56.9 | 28.2 |
| Released | 2026-08-12 | 2024-10-01 |
| Weights | Proprietary | Open |
| Context window | 500K | 262K |
| Max output | 500K | 262K |
| Input $ / M tokens | $2 | $0.15 |
| Output $ / M tokens | $6 | $0.15 |
| Results tracked | 49 | 17 |
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), Ministral 8B: 35.0 (#230)
| Benchmark | Grok 4.6 | Ministral 8B |
|---|---|---|
| LMArena Coding | 1465 | 1202 |
| DeepSWE | 67.5% | — |
| FrontierCode | 48% | — |
| CursorBench | 41.4% | — |
| LMArena WebDev | 1617 | — |
| FrontierSWE | 25.3% | — |
| SciCode | 56.5% | — |
| WeirdML | 67.3% | — |
| ALE-Bench | 1,508 | — |
Agentic & Tool Use Grok 4.6 leads
Grok 4.6: 39.4 (#27), Ministral 8B: 16.4 (#148)
| Benchmark | Grok 4.6 | Ministral 8B |
|---|---|---|
| APEX-Agents | 65.3% | — |
| Berkeley Function Calling Leaderboard | — | 11.1% |
| GDP.pdf | 17.2% | — |
| Vending-Bench 2 | 9,047 | — |
Reasoning Grok 4.6 leads
Grok 4.6: 61.4 (#20), Ministral 8B: 18.4 (#281)
| Benchmark | Grok 4.6 | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1191 |
| DTBench | 97.3% | 45.7% |
| ARC-AGI-2 | 67.1% | — |
| SimpleBench | 75.9% | — |
| NYT Connections (extended) | 80% | — |
| ARC-AGI-1 | 87.5% | — |
| CritPt | 19.7% | — |
| Chess Puzzles | 40% | — |
| EBR-Bench | 30.5% | — |
| Mystery Game Puzzles | 34% | — |
| LMCA | 48.5% | — |
| Epoch Capabilities Index | 156.44 | — |
Math Grok 4.6 leads
Grok 4.6: 67.0 (#24), Ministral 8B: 25.7 (#267)
| Benchmark | Grok 4.6 | Ministral 8B |
|---|---|---|
| LMArena Math | 1423 | 1188 |
| FrontierMath (Tiers 1-3) | 66% | — |
| FrontierMath Tier 4 | 31.7% | — |
| OTIS Mock AIME 2024-2025 | 99.2% | — |
| ProofBench | 51% | — |
| MATH Level 5 | — | 14.9% |
Knowledge Grok 4.6 leads
Grok 4.6: 63.3 (#20), Ministral 8B: 12.6 (#297)
| Benchmark | Grok 4.6 | Ministral 8B |
|---|---|---|
| GPQA Diamond | 94% | 27.1% |
| LMArena Expert | 1467 | 1170 |
| SimpleQA Verified | 49.3% | — |
| Vectara Hallucination Rate | — | 7.4% |
Multimodal Not comparable
Grok 4.6: 43.6 (#23), Ministral 8B: —
| Benchmark | Grok 4.6 | Ministral 8B |
|---|---|---|
| LMArena Vision | 1263 | — |
| Blueprint-Bench 2 | 33.2% | — |
| Furniture Assembly | 40% | — |
| LMArena Document | 1452 | — |
Multilingual Grok 4.6 leads
Grok 4.6: 53.0 (#74), Ministral 8B: 35.1 (#247)
| Benchmark | Grok 4.6 | Ministral 8B |
|---|---|---|
| LMArena Non-English | 1420 | 1165 |
| LMArena Chinese | 1480 | 1193 |
| LMArena Russian | 1422 | 1195 |
| LMArena French | 1461 | — |
| LMArena German | 1431 | — |
| LMArena Japanese | 1376 | — |
| LMArena Korean | 1397 | — |
| LMArena Spanish | 1404 | — |
Instruction Following Grok 4.6 leads
Grok 4.6: 75.4 (#63), Ministral 8B: 60.5 (#250)
| Benchmark | Grok 4.6 | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 1431 | 1161 |
Long Context Grok 4.6 leads
Grok 4.6: 44.5 (#66), Ministral 8B: 36.7 (#227)
| Benchmark | Grok 4.6 | Ministral 8B |
|---|---|---|
| LMArena Longer Query | 1454 | 1212 |
Writing & Preference Grok 4.6 leads
Grok 4.6: 62.3 (#80), Ministral 8B: 39.6 (#246)
| Benchmark | Grok 4.6 | Ministral 8B |
|---|---|---|
| LMArena Text | 1428 | 1191 |
| LMArena Creative Writing | 1428 | 1175 |
| LMArena Multi-Turn | 1425 | 1166 |
Frequently asked questions
Is Grok 4.6 better than Ministral 8B?
Grok 4.6 is the stronger model overall, scoring 56.9 to 28.2 on the Noometry Index. Ministral 8B costs 20× less per token, which makes it the better buy when Grok 4.6's lead doesn't matter for your workload.
Which is cheaper, Grok 4.6 or Ministral 8B?
Ministral 8B is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; Grok 4.6 lists at $2 and $6.
Is Grok 4.6 or Ministral 8B better for coding?
Grok 4.6 scores higher on coding benchmarks: 58.5 versus 35.0 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 Ministral 8B share?
14 benchmarks have published results for both models. Grok 4.6 has 49 scored results on Noometry and Ministral 8B has 17.