Model comparison
Llama 4 Maverick vs o1-mini
o1-mini is the stronger model overall, scoring 34.0 to 30.9 on the Noometry Index.
Last verified . 29 shared benchmarks.
MetaSummary
- They share 29 benchmarks with published results for both. Llama 4 Maverick scores higher in 3 categories and o1-mini in 6 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where o1-mini leads 48.4 to 38.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 20.6% for Llama 4 Maverick and 46.9% for o1-mini.
- Llama 4 Maverick has downloadable open weights; the other is API-only.
Side by side
| Llama 4 Maverick | o1-mini | |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 30.9 | 34.0 |
| Released | 2025-04-05 | 2024-09-12 |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.19 | — |
| Output $ / M tokens | $0.65 | — |
| Results tracked | 54 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1-mini leads
Llama 4 Maverick: 26.6 (#324), o1-mini: 35.5 (#224)
| Benchmark | Llama 4 Maverick | o1-mini |
|---|---|---|
| Aider Polyglot | 15.6% | 32.9% |
| WeirdML | 24.5% | 36.3% |
| LMArena Coding | 1302 | 1362 |
| SWE-bench Verified (bash only) | 21% | — |
| SciCode | 33.1% | — |
| BigCodeBench Instruct | 49.7% | — |
| LiveBench Coding | — | 48% |
| BigCodeBench Complete | 61.4% | — |
| ALE-Bench | 172.97 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |
Agentic & Tool Use Llama 4 Maverick leads
Llama 4 Maverick: 28.2 (#91), o1-mini: 24.6 (#118)
| Benchmark | Llama 4 Maverick | o1-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.3% | — |
| Cybench | — | 10% |
Reasoning Llama 4 Maverick leads
Llama 4 Maverick: 10.1 (#342), o1-mini: 8.8 (#346)
| Benchmark | Llama 4 Maverick | o1-mini |
|---|---|---|
| ARC-AGI-2 | 0% | 0.8% |
| SimpleBench | 27.7% | 18.1% |
| ARC-AGI-1 | 4.4% | 14% |
| LMArena Hard Prompts | 1281 | 1333 |
| Epoch Capabilities Index | 132.2 | 135.82 |
| Kagi LLM Benchmark | 55.9% | — |
| NYT Connections (extended) | 8% | — |
| CritPt | 0% | — |
| EnigmaEval | 0.6% | — |
| LiveBench Reasoning | — | 72.3% |
| DTBench | 61.9% | — |
| LiveBench Data Analysis | — | 57.9% |
| LMCA | 15.9% | — |
| ForecastBench | 57.5 | — |
| LiveBench | — | 57.8% |
Math o1-mini leads
Llama 4 Maverick: 26.0 (#262), o1-mini: 35.4 (#186)
| Benchmark | Llama 4 Maverick | o1-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 20.6% | 46.9% |
| LMArena Math | 1299 | 1358 |
| MATH Level 5 | 73% | 89.2% |
| FrontierMath (Feb 2025 set) | 0.7% | 1.7% |
| Omni-MATH | 42.2% | — |
| LiveBench Math | — | 62% |
Knowledge o1-mini leads
Llama 4 Maverick: 33.4 (#204), o1-mini: 34.9 (#192)
| Benchmark | Llama 4 Maverick | o1-mini |
|---|---|---|
| GPQA Diamond | 67% | 62.4% |
| Confabulations | 22.6% | 18.6% |
| LMArena Expert | 1259 | 1316 |
| Humanity's Last Exam | 5.7% | — |
| MMLU-Pro | 81% | — |
| Vectara Hallucination Rate | 8.2% | — |
| GPQA (HELM) | 65% | — |
Multimodal Not comparable
Llama 4 Maverick: 31.6 (#105), o1-mini: —
| Benchmark | Llama 4 Maverick | o1-mini |
|---|---|---|
| LMArena Vision | 1142 | — |
| GeoBench | 52% | — |
| SpatialViz-Bench | 31.8% | — |
Multilingual o1-mini leads
Llama 4 Maverick: 42.2 (#195), o1-mini: 43.6 (#182)
| Benchmark | Llama 4 Maverick | o1-mini |
|---|---|---|
| LMArena Non-English | 1269 | 1289 |
| LMArena Chinese | 1277 | 1314 |
| LMArena French | 1259 | 1293 |
| LMArena German | 1291 | 1278 |
| LMArena Japanese | 1207 | 1245 |
| LMArena Korean | 1203 | 1223 |
| LMArena Russian | 1286 | 1283 |
| LMArena Spanish | 1293 | 1303 |
Instruction Following Llama 4 Maverick leads
Llama 4 Maverick: 71.7 (#146), o1-mini: 66.7 (#206)
| Benchmark | Llama 4 Maverick | o1-mini |
|---|---|---|
| LMArena Instruction Following | 1267 | 1304 |
| LiveBench Instruction Following | — | 65.4% |
| IFEval | 90.8% | — |
Long Context o1-mini leads
Llama 4 Maverick: 31.4 (#279), o1-mini: 40.1 (#161)
| Benchmark | Llama 4 Maverick | o1-mini |
|---|---|---|
| LMArena Longer Query | 1280 | 1320 |
| Fiction.LiveBench | 46.2% | — |
Writing & Preference o1-mini leads
Llama 4 Maverick: 38.8 (#252), o1-mini: 48.4 (#202)
| Benchmark | Llama 4 Maverick | o1-mini |
|---|---|---|
| LMArena Text | 1287 | 1317 |
| LMArena Creative Writing | 1267 | 1244 |
| Short-Story Creative Writing | 62% | 64.9% |
| LMArena Multi-Turn | 1289 | 1314 |
| EQ-Bench Creative Writing | 860 | — |
| WildBench | 80% | — |
| LiveBench Language | — | 40.9% |
Frequently asked questions
Is Llama 4 Maverick better than o1-mini?
o1-mini is the stronger model overall, scoring 34.0 to 30.9 on the Noometry Index.
Is Llama 4 Maverick or o1-mini better for coding?
o1-mini scores higher on coding benchmarks: 35.5 versus 26.6 in the Noometry coding category.
How many benchmarks do Llama 4 Maverick and o1-mini share?
29 benchmarks have published results for both models. Llama 4 Maverick has 54 scored results on Noometry and o1-mini has 39.