Model comparison
GPT-4o mini vs Grok 4.6
Grok 4.6 is the stronger model overall, scoring 56.9 to 25.5 on the Noometry Index. GPT-4o mini costs 11× less per token, which makes it the better buy when Grok 4.6's lead doesn't matter for your workload.
Last verified . 30 shared benchmarks.
Summary
- They share 30 benchmarks with published results for both. GPT-4o mini scores higher in 0 categories and Grok 4.6 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok 4.6 leads 67.0 to 10.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.9% for GPT-4o mini and 99.2% for Grok 4.6.
- GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $2 / $6 for Grok 4.6.
- Grok 4.6 accepts more context: 500K tokens versus 128K.
Side by side
| GPT-4o mini | Grok 4.6 | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 25.5 | 56.9 |
| Released | 2024-07-18 | 2026-08-12 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 500K |
| Max output | 16K | 500K |
| Input $ / M tokens | $0.15 | $2 |
| Output $ / M tokens | $0.60 | $6 |
| Results tracked | 60 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.6 leads
GPT-4o mini: 22.0 (#335), Grok 4.6: 58.5 (#16)
| Benchmark | GPT-4o mini | Grok 4.6 |
|---|---|---|
| WeirdML | 11.8% | 67.3% |
| LMArena Coding | 1290 | 1465 |
| DeepSWE | — | 67.5% |
| FrontierCode | — | 48% |
| Aider Polyglot | 3.6% | — |
| CursorBench | — | 41.4% |
| LMArena WebDev | — | 1617 |
| FrontierSWE | — | 25.3% |
| SciCode | — | 56.5% |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 43.1% | — |
| BigCodeBench Complete | 57.4% | — |
| ALE-Bench | — | 1,508 |
| HumanEval+ | 83.5% | — |
| MBPP+ | 72.2% | — |
Agentic & Tool Use Grok 4.6 leads
GPT-4o mini: 27.5 (#101), Grok 4.6: 39.4 (#27)
| Benchmark | GPT-4o mini | Grok 4.6 |
|---|---|---|
| APEX-Agents | — | 65.3% |
| BALROG | 17.4% | — |
| GDP.pdf | — | 17.2% |
| Vending-Bench 2 | — | 9,047 |
Reasoning Grok 4.6 leads
GPT-4o mini: 8.7 (#347), Grok 4.6: 61.4 (#20)
| Benchmark | GPT-4o mini | Grok 4.6 |
|---|---|---|
| ARC-AGI-2 | 0% | 67.1% |
| SimpleBench | 10.7% | 75.9% |
| Chess Puzzles | 0% | 40% |
| LMArena Hard Prompts | 1267 | 1447 |
| Mystery Game Puzzles | 12% | 34% |
| DTBench | 54.4% | 97.3% |
| LMCA | 10.4% | 48.5% |
| Epoch Capabilities Index | 126.56 | 156.44 |
| Kagi LLM Benchmark | 28.8% | — |
| NYT Connections (extended) | — | 80% |
| ARC-AGI-1 | — | 87.5% |
| CritPt | — | 19.7% |
| EBR-Bench | — | 30.5% |
| LiveBench Reasoning | 32.8% | — |
| LiveBench Data Analysis | 50% | — |
| LiveBench | 41.3% | — |
| PIQA | 88.7% | — |
Math Grok 4.6 leads
GPT-4o mini: 10.4 (#314), Grok 4.6: 67.0 (#24)
| Benchmark | GPT-4o mini | Grok 4.6 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 0.7% | 66% |
| OTIS Mock AIME 2024-2025 | 6.9% | 99.2% |
| LMArena Math | 1267 | 1423 |
| FrontierMath Tier 4 | — | 31.7% |
| ProofBench | — | 51% |
| Omni-MATH | 28% | — |
| LiveBench Math | 36.3% | — |
| MATH Level 5 | 52.6% | — |
| GSM8K | 91.3% | — |
Knowledge Grok 4.6 leads
GPT-4o mini: 17.7 (#284), Grok 4.6: 63.3 (#20)
| Benchmark | GPT-4o mini | Grok 4.6 |
|---|---|---|
| GPQA Diamond | 37.7% | 94% |
| SimpleQA Verified | 8.3% | 49.3% |
| LMArena Expert | 1235 | 1467 |
| MMLU-Pro | 60.3% | — |
| Confabulations | 37.2% | — |
| GPQA (HELM) | 36.8% | — |
| BoolQ | 88.7% | — |
| MMLU | 81.8% | — |
Multimodal Grok 4.6 leads
GPT-4o mini: 25.9 (#122), Grok 4.6: 43.6 (#23)
| Benchmark | GPT-4o mini | Grok 4.6 |
|---|---|---|
| LMArena Vision | 1066 | 1263 |
| Video-MME | 64.8% | — |
| GeoBench | 64% | — |
| VPCT | 34% | — |
| Blueprint-Bench 2 | — | 33.2% |
| Furniture Assembly | — | 40% |
| LMArena Document | — | 1452 |
Multilingual Grok 4.6 leads
GPT-4o mini: 42.0 (#199), Grok 4.6: 53.0 (#74)
| Benchmark | GPT-4o mini | Grok 4.6 |
|---|---|---|
| LMArena Non-English | 1266 | 1420 |
| LMArena Chinese | 1265 | 1480 |
| LMArena French | 1297 | 1461 |
| LMArena German | 1272 | 1431 |
| LMArena Japanese | 1216 | 1376 |
| LMArena Korean | 1195 | 1397 |
| LMArena Russian | 1275 | 1422 |
| LMArena Spanish | 1276 | 1404 |
Instruction Following Grok 4.6 leads
GPT-4o mini: 61.9 (#239), Grok 4.6: 75.4 (#63)
| Benchmark | GPT-4o mini | Grok 4.6 |
|---|---|---|
| LMArena Instruction Following | 1258 | 1431 |
| LiveBench Instruction Following | 56.8% | — |
| IFEval | 78.2% | — |
Long Context Grok 4.6 leads
GPT-4o mini: 39.1 (#186), Grok 4.6: 44.5 (#66)
| Benchmark | GPT-4o mini | Grok 4.6 |
|---|---|---|
| LMArena Longer Query | 1289 | 1454 |
Writing & Preference Grok 4.6 leads
GPT-4o mini: 39.5 (#248), Grok 4.6: 62.3 (#80)
| Benchmark | GPT-4o mini | Grok 4.6 |
|---|---|---|
| LMArena Text | 1286 | 1428 |
| LMArena Creative Writing | 1268 | 1428 |
| LMArena Multi-Turn | 1285 | 1425 |
| Short-Story Creative Writing | 67.2% | — |
| EQ-Bench Creative Writing | 873 | — |
| WildBench | 79.1% | — |
| LiveBench Language | 28.6% | — |
Frequently asked questions
Is GPT-4o mini better than Grok 4.6?
Grok 4.6 is the stronger model overall, scoring 56.9 to 25.5 on the Noometry Index. GPT-4o mini costs 11× less per token, which makes it the better buy when Grok 4.6's lead doesn't matter for your workload.
Which is cheaper, GPT-4o mini or Grok 4.6?
GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Grok 4.6 lists at $2 and $6.
Is GPT-4o mini or Grok 4.6 better for coding?
Grok 4.6 scores higher on coding benchmarks: 58.5 versus 22.0 in the Noometry coding category.
Which has the bigger context window?
Grok 4.6 does, with 500K tokens against 128K.
How many benchmarks do GPT-4o mini and Grok 4.6 share?
30 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and Grok 4.6 has 49.