Model comparison
Llama 4 Scout vs o1
o1 is the stronger model overall, scoring 40.9 to 27.7 on the Noometry Index. Llama 4 Scout costs 175× less per token, which makes it the better buy when o1's lead doesn't matter for your workload.
Last verified . 28 shared benchmarks.
MetaSummary
- They share 28 benchmarks with published results for both. Llama 4 Scout scores higher in 0 categories and o1 in 10 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where o1 leads 46.1 to 20.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 7.8% for Llama 4 Scout and 73.3% for o1.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $15 / $60 for o1.
- o1 accepts more context: 200K tokens versus 128K.
- Llama 4 Scout has downloadable open weights; the other is API-only.
Side by side
| Llama 4 Scout | o1 | |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 27.7 | 40.9 |
| Released | 2025-04-05 | 2024-09-12 |
| Weights | Open | Proprietary |
| Context window | 128K | 200K |
| Max output | 4K | 100K |
| Input $ / M tokens | $0.10 | $15 |
| Output $ / M tokens | $0.30 | $60 |
| Results tracked | 43 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1 leads
Llama 4 Scout: 20.2 (#339), o1: 46.1 (#70)
| Benchmark | Llama 4 Scout | o1 |
|---|---|---|
| LMArena Coding | 1286 | 1367 |
| SWE-bench Verified (bash only) | 9.1% | — |
| Aider Polyglot | — | 61.7% |
| SciCode | 17% | — |
| WeirdML | — | 47.6% |
| LiveBench Coding | — | 69.7% |
| BigCodeBench Complete | 43.1% | — |
| CadEval | — | 56% |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |
Agentic & Tool Use Too close to call
Llama 4 Scout: 24.6 (#119), o1: 24.6 (#117)
| Benchmark | Llama 4 Scout | o1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.1% | — |
| Cybench | — | 10% |
| METR Time Horizons | — | 51.1% |
Reasoning o1 leads
Llama 4 Scout: 9.1 (#345), o1: 27.9 (#111)
| Benchmark | Llama 4 Scout | o1 |
|---|---|---|
| ARC-AGI-1 | 0.5% | 30.7% |
| LMArena Hard Prompts | 1266 | 1371 |
| DTBench | 57.9% | 74.7% |
| LMCA | 12% | 22.3% |
| Epoch Capabilities Index | 129.64 | 141.91 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | — | 41.7% |
| Kagi LLM Benchmark | 36.9% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 15% |
| EnigmaEval | — | 5.7% |
| LiveBench Reasoning | — | 91.6% |
| LiveBench Data Analysis | — | 65.5% |
| ForecastBench | 57.5 | — |
| LiveBench | — | 75.7% |
Math o1 leads
Llama 4 Scout: 19.6 (#286), o1: 36.1 (#175)
| Benchmark | Llama 4 Scout | o1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.8% | 73.3% |
| LMArena Math | 1287 | 1388 |
| MATH Level 5 | 62.3% | 94.7% |
| FrontierMath (Feb 2025 set) | 0% | 9.3% |
| FrontierMath (Tiers 1-3) | — | 14.7% |
| Omni-MATH | 37.3% | — |
| LiveBench Math | — | 80.3% |
Knowledge o1 leads
Llama 4 Scout: 31.9 (#217), o1: 41.5 (#110)
| Benchmark | Llama 4 Scout | o1 |
|---|---|---|
| GPQA Diamond | 51.8% | 76.8% |
| LMArena Expert | 1235 | 1361 |
| Humanity's Last Exam | — | 8% |
| SimpleQA Verified | — | 41.1% |
| MMLU-Pro | 74.2% | — |
| Confabulations | — | 11.7% |
| Vectara Hallucination Rate | 7.7% | — |
| GPQA (HELM) | 50.7% | — |
Multimodal o1 leads
Llama 4 Scout: 32.2 (#102), o1: 34.2 (#93)
| Benchmark | Llama 4 Scout | o1 |
|---|---|---|
| LMArena Vision | 1118 | 1168 |
| SpatialViz-Bench | 34.2% | 41.4% |
| GeoBench | — | 80% |
| VPCT | — | 37% |
Multilingual o1 leads
Llama 4 Scout: 41.0 (#212), o1: 48.6 (#142)
| Benchmark | Llama 4 Scout | o1 |
|---|---|---|
| LMArena Non-English | 1252 | 1358 |
| LMArena Chinese | 1255 | 1394 |
| LMArena French | 1282 | 1344 |
| LMArena German | 1272 | 1337 |
| LMArena Japanese | 1206 | 1346 |
| LMArena Korean | 1207 | 1396 |
| LMArena Russian | 1263 | 1356 |
| LMArena Spanish | 1278 | 1345 |
Instruction Following o1 leads
Llama 4 Scout: 65.8 (#217), o1: 74.8 (#86)
| Benchmark | Llama 4 Scout | o1 |
|---|---|---|
| LMArena Instruction Following | 1248 | 1367 |
| LiveBench Instruction Following | — | 81.5% |
| IFEval | 81.8% | — |
Long Context o1 leads
Llama 4 Scout: 27.5 (#294), o1: 50.3 (#9)
| Benchmark | Llama 4 Scout | o1 |
|---|---|---|
| Fiction.LiveBench | 36% | 83.3% |
| LMArena Longer Query | 1265 | 1378 |
Writing & Preference o1 leads
Llama 4 Scout: 37.0 (#261), o1: 55.6 (#144)
| Benchmark | Llama 4 Scout | o1 |
|---|---|---|
| LMArena Text | 1279 | 1366 |
| LMArena Creative Writing | 1249 | 1348 |
| LMArena Multi-Turn | 1280 | 1369 |
| Short-Story Creative Writing | — | 70.2% |
| EQ-Bench Creative Writing | 783 | — |
| WildBench | 78% | — |
| LiveBench Language | — | 65.4% |
Frequently asked questions
Is Llama 4 Scout better than o1?
o1 is the stronger model overall, scoring 40.9 to 27.7 on the Noometry Index. Llama 4 Scout costs 175× less per token, which makes it the better buy when o1's lead doesn't matter for your workload.
Which is cheaper, Llama 4 Scout or o1?
Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; o1 lists at $15 and $60.
Is Llama 4 Scout or o1 better for coding?
o1 scores higher on coding benchmarks: 46.1 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
o1 does, with 200K tokens against 128K.
How many benchmarks do Llama 4 Scout and o1 share?
28 benchmarks have published results for both models. Llama 4 Scout has 43 scored results on Noometry and o1 has 52.