Model comparison
Llama 4 Scout vs o1-mini
o1-mini is the stronger model overall, scoring 34.0 to 27.7 on the Noometry Index.
Last verified . 24 shared benchmarks.
MetaSummary
- They share 24 benchmarks with published results for both. Llama 4 Scout scores higher in 1 category and o1-mini in 8 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where o1-mini leads 35.4 to 19.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 7.8% for Llama 4 Scout and 46.9% for o1-mini.
- Llama 4 Scout has downloadable open weights; the other is API-only.
Side by side
| Llama 4 Scout | o1-mini | |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 27.7 | 34.0 |
| Released | 2025-04-05 | 2024-09-12 |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.30 | — |
| Results tracked | 43 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1-mini leads
Llama 4 Scout: 20.2 (#339), o1-mini: 35.5 (#224)
| Benchmark | Llama 4 Scout | o1-mini |
|---|---|---|
| LMArena Coding | 1286 | 1362 |
| SWE-bench Verified (bash only) | 9.1% | — |
| Aider Polyglot | — | 32.9% |
| SciCode | 17% | — |
| WeirdML | — | 36.3% |
| LiveBench Coding | — | 48% |
| BigCodeBench Complete | 43.1% | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |
Agentic & Tool Use Too close to call
Llama 4 Scout: 24.6 (#119), o1-mini: 24.6 (#118)
| Benchmark | Llama 4 Scout | o1-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.1% | — |
| Cybench | — | 10% |
Reasoning Too close to call
Llama 4 Scout: 9.1 (#345), o1-mini: 8.8 (#346)
| Benchmark | Llama 4 Scout | o1-mini |
|---|---|---|
| ARC-AGI-2 | 0% | 0.8% |
| ARC-AGI-1 | 0.5% | 14% |
| LMArena Hard Prompts | 1266 | 1333 |
| Epoch Capabilities Index | 129.64 | 135.82 |
| SimpleBench | — | 18.1% |
| Kagi LLM Benchmark | 36.9% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | — | 72.3% |
| DTBench | 57.9% | — |
| LiveBench Data Analysis | — | 57.9% |
| LMCA | 12% | — |
| ForecastBench | 57.5 | — |
| LiveBench | — | 57.8% |
Math o1-mini leads
Llama 4 Scout: 19.6 (#286), o1-mini: 35.4 (#186)
| Benchmark | Llama 4 Scout | o1-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.8% | 46.9% |
| LMArena Math | 1287 | 1358 |
| MATH Level 5 | 62.3% | 89.2% |
| FrontierMath (Feb 2025 set) | 0% | 1.7% |
| Omni-MATH | 37.3% | — |
| LiveBench Math | — | 62% |
Knowledge o1-mini leads
Llama 4 Scout: 31.9 (#217), o1-mini: 34.9 (#192)
| Benchmark | Llama 4 Scout | o1-mini |
|---|---|---|
| GPQA Diamond | 51.8% | 62.4% |
| LMArena Expert | 1235 | 1316 |
| MMLU-Pro | 74.2% | — |
| Confabulations | — | 18.6% |
| Vectara Hallucination Rate | 7.7% | — |
| GPQA (HELM) | 50.7% | — |
Multimodal Not comparable
Llama 4 Scout: 32.2 (#102), o1-mini: —
| Benchmark | Llama 4 Scout | o1-mini |
|---|---|---|
| LMArena Vision | 1118 | — |
| SpatialViz-Bench | 34.2% | — |
Multilingual o1-mini leads
Llama 4 Scout: 41.0 (#212), o1-mini: 43.6 (#182)
| Benchmark | Llama 4 Scout | o1-mini |
|---|---|---|
| LMArena Non-English | 1252 | 1289 |
| LMArena Chinese | 1255 | 1314 |
| LMArena French | 1282 | 1293 |
| LMArena German | 1272 | 1278 |
| LMArena Japanese | 1206 | 1245 |
| LMArena Korean | 1207 | 1223 |
| LMArena Russian | 1263 | 1283 |
| LMArena Spanish | 1278 | 1303 |
Instruction Following Too close to call
Llama 4 Scout: 65.8 (#217), o1-mini: 66.7 (#206)
| Benchmark | Llama 4 Scout | o1-mini |
|---|---|---|
| LMArena Instruction Following | 1248 | 1304 |
| LiveBench Instruction Following | — | 65.4% |
| IFEval | 81.8% | — |
Long Context o1-mini leads
Llama 4 Scout: 27.5 (#294), o1-mini: 40.1 (#161)
| Benchmark | Llama 4 Scout | o1-mini |
|---|---|---|
| LMArena Longer Query | 1265 | 1320 |
| Fiction.LiveBench | 36% | — |
Writing & Preference o1-mini leads
Llama 4 Scout: 37.0 (#261), o1-mini: 48.4 (#202)
| Benchmark | Llama 4 Scout | o1-mini |
|---|---|---|
| LMArena Text | 1279 | 1317 |
| LMArena Creative Writing | 1249 | 1244 |
| LMArena Multi-Turn | 1280 | 1314 |
| Short-Story Creative Writing | — | 64.9% |
| EQ-Bench Creative Writing | 783 | — |
| WildBench | 78% | — |
| LiveBench Language | — | 40.9% |
Frequently asked questions
Is Llama 4 Scout better than o1-mini?
o1-mini is the stronger model overall, scoring 34.0 to 27.7 on the Noometry Index.
Is Llama 4 Scout or o1-mini better for coding?
o1-mini scores higher on coding benchmarks: 35.5 versus 20.2 in the Noometry coding category.
How many benchmarks do Llama 4 Scout and o1-mini share?
24 benchmarks have published results for both models. Llama 4 Scout has 43 scored results on Noometry and o1-mini has 39.