Model comparison
Grok 4.6 vs o4-mini
Grok 4.6 is the stronger model overall, scoring 56.9 to 41.6 on the Noometry Index. o4-mini costs 1.6× less per token, which makes it the better buy when Grok 4.6's lead doesn't matter for your workload.
Last verified . 34 shared benchmarks.
Summary
- They share 34 benchmarks with published results for both. Grok 4.6 scores higher in 9 categories and o4-mini in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.6 leads 61.4 to 24.6.
- The biggest single-benchmark swing is ARC-AGI-2: 67.1% for Grok 4.6 and 6.1% for o4-mini.
- o4-mini is cheaper at $1.10 / $4.40 per million input/output tokens, against $2 / $6 for Grok 4.6.
- Grok 4.6 accepts more context: 500K tokens versus 200K.
Side by side
| Grok 4.6 | o4-mini | |
|---|---|---|
| Provider | xAI | OpenAI |
| Noometry Index | 56.9 | 41.6 |
| Released | 2026-08-12 | 2025-04-16 |
| Weights | Proprietary | Proprietary |
| Context window | 500K | 200K |
| Max output | 500K | 100K |
| Input $ / M tokens | $2 | $1.10 |
| Output $ / M tokens | $6 | $4.40 |
| Results tracked | 49 | 60 |
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), o4-mini: 40.9 (#127)
| Benchmark | Grok 4.6 | o4-mini |
|---|---|---|
| WeirdML | 67.3% | 52.6% |
| LMArena Coding | 1465 | 1368 |
| ALE-Bench | 1,508 | 826.17 |
| DeepSWE | 67.5% | — |
| FrontierCode | 48% | — |
| SWE-bench Verified (bash only) | — | 45% |
| Aider Polyglot | — | 72% |
| CursorBench | 41.4% | — |
| LMArena WebDev | 1617 | — |
| FrontierSWE | 25.3% | — |
| SciCode | 56.5% | — |
| GSO | — | 3.6% |
| CadEval | — | 62% |
| AlgoTune | — | 1.72 |
Agentic & Tool Use Grok 4.6 leads
Grok 4.6: 39.4 (#27), o4-mini: 32.6 (#61)
| Benchmark | Grok 4.6 | o4-mini |
|---|---|---|
| APEX-Agents | 65.3% | — |
| Berkeley Function Calling Leaderboard | — | 53.2% |
| GDPval | — | 25.3% |
| GDP.pdf | 17.2% | — |
| METR Time Horizons | — | 63.9% |
| Vending-Bench 2 | 9,047 | — |
Reasoning Grok 4.6 leads
Grok 4.6: 61.4 (#20), o4-mini: 24.6 (#162)
| Benchmark | Grok 4.6 | o4-mini |
|---|---|---|
| ARC-AGI-2 | 67.1% | 6.1% |
| SimpleBench | 75.9% | 38.7% |
| ARC-AGI-1 | 87.5% | 58.7% |
| CritPt | 19.7% | 0.6% |
| Chess Puzzles | 40% | 26% |
| LMArena Hard Prompts | 1447 | 1351 |
| Mystery Game Puzzles | 34% | 5% |
| DTBench | 97.3% | 77.6% |
| LMCA | 48.5% | 26.5% |
| Epoch Capabilities Index | 156.44 | 145.64 |
| Kagi LLM Benchmark | — | 67.6% |
| NYT Connections (extended) | 80% | — |
| EnigmaEval | — | 9.2% |
| EBR-Bench | 30.5% | — |
| ForecastBench | — | 61.8 |
Math Grok 4.6 leads
Grok 4.6: 67.0 (#24), o4-mini: 40.8 (#89)
| Benchmark | Grok 4.6 | o4-mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 66% | 36.1% |
| FrontierMath Tier 4 | 31.7% | 4.9% |
| OTIS Mock AIME 2024-2025 | 99.2% | 81.7% |
| LMArena Math | 1423 | 1389 |
| ProofBench | 51% | — |
| Omni-MATH | — | 72% |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 24.8% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge Grok 4.6 leads
Grok 4.6: 63.3 (#20), o4-mini: 43.6 (#91)
| Benchmark | Grok 4.6 | o4-mini |
|---|---|---|
| GPQA Diamond | 94% | 79.6% |
| SimpleQA Verified | 49.3% | 19.6% |
| LMArena Expert | 1467 | 1343 |
| Humanity's Last Exam | — | 18.1% |
| MMLU-Pro | — | 82% |
| Confabulations | — | 15.8% |
| Vectara Hallucination Rate | — | 18.6% |
| GPQA (HELM) | — | 73.5% |
Multimodal Grok 4.6 leads
Grok 4.6: 43.6 (#23), o4-mini: 40.2 (#49)
| Benchmark | Grok 4.6 | o4-mini |
|---|---|---|
| LMArena Vision | 1263 | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |
| Blueprint-Bench 2 | 33.2% | — |
| Furniture Assembly | 40% | — |
| LMArena Document | 1452 | — |
Multilingual Grok 4.6 leads
Grok 4.6: 53.0 (#74), o4-mini: 47.0 (#154)
| Benchmark | Grok 4.6 | o4-mini |
|---|---|---|
| LMArena Non-English | 1420 | 1337 |
| LMArena Chinese | 1480 | 1354 |
| LMArena French | 1461 | 1364 |
| LMArena German | 1431 | 1336 |
| LMArena Japanese | 1376 | 1308 |
| LMArena Korean | 1397 | 1312 |
| LMArena Russian | 1422 | 1334 |
| LMArena Spanish | 1404 | 1347 |
Instruction Following Too close to call
Grok 4.6: 75.4 (#63), o4-mini: 75.2 (#68)
| Benchmark | Grok 4.6 | o4-mini |
|---|---|---|
| LMArena Instruction Following | 1431 | 1321 |
| IFEval | — | 92.8% |
Long Context o4-mini leads
Grok 4.6: 44.5 (#66), o4-mini: 45.5 (#33)
| Benchmark | Grok 4.6 | o4-mini |
|---|---|---|
| LMArena Longer Query | 1454 | 1315 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference Grok 4.6 leads
Grok 4.6: 62.3 (#80), o4-mini: 54.0 (#152)
| Benchmark | Grok 4.6 | o4-mini |
|---|---|---|
| LMArena Text | 1428 | 1353 |
| LMArena Creative Writing | 1428 | 1294 |
| LMArena Multi-Turn | 1425 | 1350 |
| Short-Story Creative Writing | — | 75% |
| WildBench | — | 85.4% |
Frequently asked questions
Is Grok 4.6 better than o4-mini?
Grok 4.6 is the stronger model overall, scoring 56.9 to 41.6 on the Noometry Index. o4-mini costs 1.6× 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 o4-mini?
o4-mini is cheaper. It lists at $1.10 per million input tokens and $4.40 per million output tokens; Grok 4.6 lists at $2 and $6.
Is Grok 4.6 or o4-mini better for coding?
Grok 4.6 scores higher on coding benchmarks: 58.5 versus 40.9 in the Noometry coding category.
Which has the bigger context window?
Grok 4.6 does, with 500K tokens against 200K.
How many benchmarks do Grok 4.6 and o4-mini share?
34 benchmarks have published results for both models. Grok 4.6 has 49 scored results on Noometry and o4-mini has 60.