Model comparison
GPT-5 Mini vs Llama 3.1-405B
GPT-5 Mini is the stronger model overall, scoring 41.7 to 30.4 on the Noometry Index.
Last verified . 32 shared benchmarks.
MetaSummary
- They share 32 benchmarks with published results for both. GPT-5 Mini scores higher in 9 categories and Llama 3.1-405B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5 Mini leads 46.3 to 17.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 86.7% for GPT-5 Mini and 9.7% for Llama 3.1-405B.
- Llama 3.1-405B has downloadable open weights; the other is API-only.
Side by side
| GPT-5 Mini | Llama 3.1-405B | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 41.7 | 30.4 |
| Released | 2025-08-07 | 2024-07-23 |
| Weights | Proprietary | Open |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $2 | — |
| Results tracked | 60 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 Mini leads
GPT-5 Mini: 40.0 (#134), Llama 3.1-405B: 32.7 (#257)
| Benchmark | GPT-5 Mini | Llama 3.1-405B |
|---|---|---|
| WeirdML | 52.7% | 21.4% |
| LMArena Coding | 1406 | 1291 |
| SWE-bench Verified | 64.7% | — |
| SWE-bench Verified (bash only) | 59.8% | — |
| SWE-bench Multilingual | 39.7% | — |
| SciCode | 39.2% | — |
| ALE-Bench | 799.77 | — |
| AlgoTune | 1.38 | — |
Agentic & Tool Use GPT-5 Mini leads
GPT-5 Mini: 31.0 (#64), Llama 3.1-405B: 20.9 (#131)
| Benchmark | GPT-5 Mini | Llama 3.1-405B |
|---|---|---|
| Terminal-Bench | 34.8% | — |
| Berkeley Function Calling Leaderboard | 55.5% | — |
| TheAgentCompany | — | 7.4% |
| Cybench | — | 7.5% |
| Vending-Bench 2 | -31.18 | — |
Reasoning GPT-5 Mini leads
GPT-5 Mini: 24.1 (#153), Llama 3.1-405B: 16.4 (#293)
| Benchmark | GPT-5 Mini | Llama 3.1-405B |
|---|---|---|
| Kagi LLM Benchmark | 70.3% | 45% |
| LMArena Hard Prompts | 1380 | 1270 |
| DTBench | 80.5% | 61.4% |
| Epoch Capabilities Index | 145.51 | 128.76 |
| ForecastBench | 61 | 59.9 |
| ARC-AGI-2 | 4.4% | — |
| SimpleBench | — | 23% |
| ARC-AGI-1 | 54.3% | — |
| CritPt | 0% | — |
| Chess Puzzles | 30% | — |
| EnigmaEval | 8.2% | — |
| Mystery Game Puzzles | 10% | — |
| LMCA | 34.2% | — |
| BIG-Bench Hard | — | 82.9% |
| HellaSwag | — | 89.2% |
| PIQA | — | 85.9% |
| WinoGrande | — | 89.2% |
Math GPT-5 Mini leads
GPT-5 Mini: 46.3 (#59), Llama 3.1-405B: 17.3 (#283)
| Benchmark | GPT-5 Mini | Llama 3.1-405B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 86.7% | 9.7% |
| Omni-MATH | 72.2% | 24.9% |
| LMArena Math | 1377 | 1281 |
| MATH Level 5 | 97.8% | 49.8% |
| FrontierMath (Tiers 1-3) | 46.7% | — |
| FrontierMath Tier 4 | 12.2% | — |
| ProofBench | 9% | — |
| FrontierMath (Feb 2025 set) | 27.2% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |
Knowledge GPT-5 Mini leads
GPT-5 Mini: 45.5 (#80), Llama 3.1-405B: 30.4 (#221)
| Benchmark | GPT-5 Mini | Llama 3.1-405B |
|---|---|---|
| GPQA Diamond | 75% | 50.9% |
| MMLU-Pro | 83.5% | 72.3% |
| Confabulations | 13.3% | 17.6% |
| GPQA (HELM) | 75.6% | 52.2% |
| LMArena Expert | 1377 | 1243 |
| Humanity's Last Exam | 19.4% | — |
| SimpleQA Verified | 21.6% | — |
| Vectara Hallucination Rate | 12.9% | — |
| ARC (AI2) Challenge | — | 95.3% |
| MMLU | — | 84.5% |
| TriviaQA | — | 82.7% |
Multimodal Not comparable
GPT-5 Mini: 35.0 (#80), Llama 3.1-405B: —
| Benchmark | GPT-5 Mini | Llama 3.1-405B |
|---|---|---|
| LMArena Vision | 1202 | — |
| VPCT | 40.2% | — |
Multilingual GPT-5 Mini leads
GPT-5 Mini: 49.1 (#131), Llama 3.1-405B: 40.9 (#209)
| Benchmark | GPT-5 Mini | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | 1363 | 1248 |
| LMArena Chinese | 1387 | 1242 |
| LMArena French | 1385 | 1278 |
| LMArena German | 1366 | 1252 |
| LMArena Japanese | 1342 | 1208 |
| LMArena Korean | 1306 | 1184 |
| LMArena Russian | 1362 | 1265 |
| LMArena Spanish | 1355 | 1259 |
Instruction Following GPT-5 Mini leads
GPT-5 Mini: 76.4 (#43), Llama 3.1-405B: 66.1 (#209)
| Benchmark | GPT-5 Mini | Llama 3.1-405B |
|---|---|---|
| IFEval | 92.7% | 81.1% |
| LMArena Instruction Following | 1357 | 1259 |
Long Context GPT-5 Mini leads
GPT-5 Mini: 41.9 (#127), Llama 3.1-405B: 38.4 (#192)
| Benchmark | GPT-5 Mini | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | 1355 | 1266 |
| Fiction.LiveBench | 69.4% | — |
Writing & Preference GPT-5 Mini leads
GPT-5 Mini: 55.4 (#143), Llama 3.1-405B: 39.1 (#246)
| Benchmark | GPT-5 Mini | Llama 3.1-405B |
|---|---|---|
| LMArena Text | 1373 | 1284 |
| LMArena Creative Writing | 1325 | 1262 |
| EQ-Bench Creative Writing | 1313 | 870 |
| WildBench | 85.5% | 78.3% |
| LMArena Multi-Turn | 1363 | 1297 |
| Short-Story Creative Writing | 83.1% | — |
Frequently asked questions
Is GPT-5 Mini better than Llama 3.1-405B?
GPT-5 Mini is the stronger model overall, scoring 41.7 to 30.4 on the Noometry Index.
Is GPT-5 Mini or Llama 3.1-405B better for coding?
GPT-5 Mini scores higher on coding benchmarks: 40.0 versus 32.7 in the Noometry coding category.
How many benchmarks do GPT-5 Mini and Llama 3.1-405B share?
32 benchmarks have published results for both models. GPT-5 Mini has 60 scored results on Noometry and Llama 3.1-405B has 42.