Model comparison
GPT-4o mini vs Llama 3.1-405B
Llama 3.1-405B is the stronger model overall, scoring 30.7 to 25.5 on the Noometry Index.
Last verified . 34 shared benchmarks.
MetaSummary
- They share 34 benchmarks with published results for both. GPT-4o mini scores higher in 4 categories and Llama 3.1-405B in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 3.1-405B leads 30.4 to 17.7.
- The biggest single-benchmark swing is Confabulations: 37.2% for GPT-4o mini and 17.6% for Llama 3.1-405B.
- Llama 3.1-405B has downloadable open weights; the other is API-only.
Side by side
| GPT-4o mini | Llama 3.1-405B | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 25.5 | 30.7 |
| Released | 2024-07-18 | 2024-07-23 |
| Weights | Proprietary | Open |
| Context window | 128K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 60 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3.1-405B leads
GPT-4o mini: 22.0 (#335), Llama 3.1-405B: 33.1 (#262)
| Benchmark | GPT-4o mini | Llama 3.1-405B |
|---|---|---|
| WeirdML | 11.8% | 21.4% |
| LMArena Coding | 1290 | 1291 |
| Aider Polyglot | 3.6% | — |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 43.1% | — |
| BigCodeBench Complete | 57.4% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 72.2% | — |
Agentic & Tool Use GPT-4o mini leads
GPT-4o mini: 27.5 (#101), Llama 3.1-405B: 21.0 (#140)
| Benchmark | GPT-4o mini | Llama 3.1-405B |
|---|---|---|
| TheAgentCompany | — | 7.4% |
| Cybench | — | 7.5% |
| BALROG | 17.4% | — |
Reasoning Llama 3.1-405B leads
GPT-4o mini: 8.7 (#347), Llama 3.1-405B: 16.8 (#300)
| Benchmark | GPT-4o mini | Llama 3.1-405B |
|---|---|---|
| SimpleBench | 10.7% | 23% |
| Kagi LLM Benchmark | 28.8% | 45% |
| LMArena Hard Prompts | 1267 | 1269 |
| DTBench | 54.4% | 61.4% |
| Epoch Capabilities Index | 126.56 | 128.75 |
| PIQA | 88.7% | 85.9% |
| ARC-AGI-2 | 0% | — |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 32.8% | — |
| Mystery Game Puzzles | 12% | — |
| LiveBench Data Analysis | 50% | — |
| LMCA | 10.4% | — |
| BIG-Bench Hard | — | 82.9% |
| ForecastBench | — | 59.9 |
| HellaSwag | — | 89.2% |
| LiveBench | 41.3% | — |
| WinoGrande | — | 89.2% |
Math Llama 3.1-405B leads
GPT-4o mini: 10.4 (#314), Llama 3.1-405B: 18.4 (#290)
| Benchmark | GPT-4o mini | Llama 3.1-405B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.9% | 9.7% |
| Omni-MATH | 28% | 24.9% |
| LMArena Math | 1267 | 1281 |
| MATH Level 5 | 52.6% | 49.8% |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| LiveBench Math | 36.3% | — |
| GSM8K | 91.3% | — |
Knowledge Llama 3.1-405B leads
GPT-4o mini: 17.7 (#284), Llama 3.1-405B: 30.4 (#227)
| Benchmark | GPT-4o mini | Llama 3.1-405B |
|---|---|---|
| GPQA Diamond | 37.7% | 50.9% |
| MMLU-Pro | 60.3% | 72.3% |
| Confabulations | 37.2% | 17.6% |
| GPQA (HELM) | 36.8% | 52.2% |
| LMArena Expert | 1235 | 1243 |
| MMLU | 81.8% | 84.5% |
| SimpleQA Verified | 8.3% | — |
| ARC (AI2) Challenge | — | 95.3% |
| BoolQ | 88.7% | — |
| TriviaQA | — | 82.7% |
Multimodal Not comparable
GPT-4o mini: 25.9 (#122), Llama 3.1-405B: —
| Benchmark | GPT-4o mini | Llama 3.1-405B |
|---|---|---|
| LMArena Vision | 1066 | — |
| Video-MME | 64.8% | — |
| GeoBench | 64% | — |
| VPCT | 34% | — |
Multilingual GPT-4o mini leads
GPT-4o mini: 42.0 (#199), Llama 3.1-405B: 40.7 (#214)
| Benchmark | GPT-4o mini | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | 1266 | 1248 |
| LMArena Chinese | 1265 | 1242 |
| LMArena French | 1297 | 1279 |
| LMArena German | 1272 | 1252 |
| LMArena Japanese | 1216 | 1208 |
| LMArena Korean | 1195 | 1184 |
| LMArena Russian | 1275 | 1265 |
| LMArena Spanish | 1276 | 1260 |
Instruction Following Llama 3.1-405B leads
GPT-4o mini: 61.9 (#239), Llama 3.1-405B: 65.9 (#214)
| Benchmark | GPT-4o mini | Llama 3.1-405B |
|---|---|---|
| IFEval | 78.2% | 81.1% |
| LMArena Instruction Following | 1258 | 1259 |
| LiveBench Instruction Following | 56.8% | — |
Long Context Too close to call
GPT-4o mini: 39.1 (#186), Llama 3.1-405B: 38.4 (#197)
| Benchmark | GPT-4o mini | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | 1289 | 1266 |
Writing & Preference Too close to call
GPT-4o mini: 39.5 (#248), Llama 3.1-405B: 38.9 (#251)
| Benchmark | GPT-4o mini | Llama 3.1-405B |
|---|---|---|
| LMArena Text | 1286 | 1284 |
| LMArena Creative Writing | 1268 | 1262 |
| EQ-Bench Creative Writing | 873 | 870 |
| WildBench | 79.1% | 78.3% |
| LMArena Multi-Turn | 1285 | 1297 |
| Short-Story Creative Writing | 67.2% | — |
| LiveBench Language | 28.6% | — |
Frequently asked questions
Is GPT-4o mini better than Llama 3.1-405B?
Llama 3.1-405B is the stronger model overall, scoring 30.7 to 25.5 on the Noometry Index.
Is GPT-4o mini or Llama 3.1-405B better for coding?
Llama 3.1-405B scores higher on coding benchmarks: 33.1 versus 22.0 in the Noometry coding category.
How many benchmarks do GPT-4o mini and Llama 3.1-405B share?
34 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and Llama 3.1-405B has 42.