Model comparison
GPT-4.1 mini vs Grok 4.6
Grok 4.6 is the stronger model overall, scoring 56.9 to 33.6 on the Noometry Index. GPT-4.1 mini costs 4.3× less per token, which makes it the better buy when Grok 4.6's lead doesn't matter for your workload.
Last verified . 32 shared benchmarks.
Summary
- They share 32 benchmarks with published results for both. GPT-4.1 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 reasoning, where Grok 4.6 leads 61.4 to 10.8.
- The biggest single-benchmark swing is ARC-AGI-1: 3.5% for GPT-4.1 mini and 87.5% for Grok 4.6.
- GPT-4.1 mini is cheaper at $0.40 / $1.60 per million input/output tokens, against $2 / $6 for Grok 4.6.
- GPT-4.1 mini accepts more context: 1.05M tokens versus 500K.
Side by side
| GPT-4.1 mini | Grok 4.6 | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 33.6 | 56.9 |
| Released | 2025-04-14 | 2026-08-12 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 500K |
| Max output | 33K | 500K |
| Input $ / M tokens | $0.40 | $2 |
| Output $ / M tokens | $1.60 | $6 |
| Results tracked | 47 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.6 leads
GPT-4.1 mini: 30.6 (#293), Grok 4.6: 58.5 (#16)
| Benchmark | GPT-4.1 mini | Grok 4.6 |
|---|---|---|
| SciCode | 40.4% | 56.5% |
| WeirdML | 37.6% | 67.3% |
| LMArena Coding | 1367 | 1465 |
| DeepSWE | — | 67.5% |
| FrontierCode | — | 48% |
| SWE-bench Verified (bash only) | 23.9% | — |
| Aider Polyglot | 32.4% | — |
| CursorBench | — | 41.4% |
| LMArena WebDev | — | 1617 |
| FrontierSWE | — | 25.3% |
| BigCodeBench Instruct | 48.9% | — |
| CadEval | 16% | — |
| ALE-Bench | — | 1,508 |
Agentic & Tool Use Grok 4.6 leads
GPT-4.1 mini: 33.3 (#55), Grok 4.6: 39.4 (#27)
| Benchmark | GPT-4.1 mini | Grok 4.6 |
|---|---|---|
| APEX-Agents | — | 65.3% |
| Berkeley Function Calling Leaderboard | 50.5% | — |
| GDP.pdf | — | 17.2% |
| Vending-Bench 2 | — | 9,047 |
Reasoning Grok 4.6 leads
GPT-4.1 mini: 10.8 (#340), Grok 4.6: 61.4 (#20)
| Benchmark | GPT-4.1 mini | Grok 4.6 |
|---|---|---|
| ARC-AGI-2 | 0% | 67.1% |
| ARC-AGI-1 | 3.5% | 87.5% |
| CritPt | 0% | 19.7% |
| Chess Puzzles | 7% | 40% |
| LMArena Hard Prompts | 1349 | 1447 |
| Mystery Game Puzzles | 7% | 34% |
| DTBench | 68.8% | 97.3% |
| LMCA | 21.1% | 48.5% |
| Epoch Capabilities Index | 135.01 | 156.44 |
| SimpleBench | — | 75.9% |
| Kagi LLM Benchmark | 48.6% | — |
| NYT Connections (extended) | — | 80% |
| EBR-Bench | — | 30.5% |
Math Grok 4.6 leads
GPT-4.1 mini: 24.1 (#270), Grok 4.6: 67.0 (#24)
| Benchmark | GPT-4.1 mini | Grok 4.6 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 6.7% | 66% |
| OTIS Mock AIME 2024-2025 | 44.7% | 99.2% |
| LMArena Math | 1343 | 1423 |
| FrontierMath Tier 4 | — | 31.7% |
| ProofBench | — | 51% |
| Omni-MATH | 49.1% | — |
| MATH Level 5 | 87.3% | — |
| FrontierMath (Feb 2025 set) | 4.5% | — |
Knowledge Grok 4.6 leads
GPT-4.1 mini: 34.7 (#194), Grok 4.6: 63.3 (#20)
| Benchmark | GPT-4.1 mini | Grok 4.6 |
|---|---|---|
| GPQA Diamond | 65.8% | 94% |
| SimpleQA Verified | 12.7% | 49.3% |
| LMArena Expert | 1338 | 1467 |
| MMLU-Pro | 78.3% | — |
| GPQA (HELM) | 61.4% | — |
Multimodal Grok 4.6 leads
GPT-4.1 mini: 35.8 (#82), Grok 4.6: 43.6 (#23)
| Benchmark | GPT-4.1 mini | Grok 4.6 |
|---|---|---|
| LMArena Vision | 1181 | 1263 |
| Blueprint-Bench 2 | — | 33.2% |
| Furniture Assembly | — | 40% |
| LMArena Document | — | 1452 |
Multilingual Grok 4.6 leads
GPT-4.1 mini: 45.7 (#166), Grok 4.6: 53.0 (#74)
| Benchmark | GPT-4.1 mini | Grok 4.6 |
|---|---|---|
| LMArena Non-English | 1318 | 1420 |
| LMArena Chinese | 1329 | 1480 |
| LMArena French | 1358 | 1461 |
| LMArena German | 1351 | 1431 |
| LMArena Japanese | 1290 | 1376 |
| LMArena Korean | 1298 | 1397 |
| LMArena Russian | 1324 | 1422 |
| LMArena Spanish | 1319 | 1404 |
Instruction Following Grok 4.6 leads
GPT-4.1 mini: 73.7 (#118), Grok 4.6: 75.4 (#63)
| Benchmark | GPT-4.1 mini | Grok 4.6 |
|---|---|---|
| LMArena Instruction Following | 1333 | 1431 |
| IFEval | 90.4% | — |
Long Context Grok 4.6 leads
GPT-4.1 mini: 31.8 (#275), Grok 4.6: 44.5 (#66)
| Benchmark | GPT-4.1 mini | Grok 4.6 |
|---|---|---|
| LMArena Longer Query | 1344 | 1454 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference Grok 4.6 leads
GPT-4.1 mini: 48.6 (#199), Grok 4.6: 62.3 (#80)
| Benchmark | GPT-4.1 mini | Grok 4.6 |
|---|---|---|
| LMArena Text | 1340 | 1428 |
| LMArena Creative Writing | 1300 | 1428 |
| LMArena Multi-Turn | 1354 | 1425 |
| EQ-Bench Creative Writing | 1147 | — |
| WildBench | 83.8% | — |
Frequently asked questions
Is GPT-4.1 mini better than Grok 4.6?
Grok 4.6 is the stronger model overall, scoring 56.9 to 33.6 on the Noometry Index. GPT-4.1 mini costs 4.3× 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-4.1 mini or Grok 4.6?
GPT-4.1 mini is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; Grok 4.6 lists at $2 and $6.
Is GPT-4.1 mini or Grok 4.6 better for coding?
Grok 4.6 scores higher on coding benchmarks: 58.5 versus 30.6 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 mini does, with 1.05M tokens against 500K.
How many benchmarks do GPT-4.1 mini and Grok 4.6 share?
32 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and Grok 4.6 has 49.