MetaLlama 3.1 405B
Llama 3.1 405B is a Meta open-weights model, released 23 Jul 2024. Its best configuration ranks #580 of 785 on the BenchLeader Index at 42.9 ±3.4, in the lower half. The ± is the point: 285 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in knowledge (54) and lowest in coding (35). Last measured 22 Oct 2026.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- 128k
- Full answer
- –
- Cost per run
- –
- Released
- 23 Jul 2024
- Overall index43
- Reasoning38
- Coding35
- Agents & tools38
- Maths42
- Knowledge54
- Instruction following46
- Human preference50
- Long context37
- Composite38
Versions
Meta has shipped 2 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| Llama 3.1 405Bthis page | 23 Jul 2024 | 42.9 | #580 |
| Llama 3 405B | – | – | – |
How its index has moved
8 Sept 2026 to 18 Oct 2026The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| GPQA Diamond | 50.9%#213 | Epoch AI Benchmarking Hub | |
| SimpleBench | 23.0%#76 | SimpleBench | |
| Arena Hard Prompts | 1342#221 | Arena (LMArena) | |
| GPQA Diamond (AA)not in index | 51.5%#421 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 4.0%#554 | Artificial Analysis | |
| GPQA Diamond (HELM)not in index | 52.2%#34 | HELM Capabilities | |
| CritPt | 0.0%#315 | Artificial Analysis | |
| DTBenchnot in index | 61.4%#180 | Epoch AI Benchmarking Hub | |
| ForecastBenchnot in index | 62.6%#53 | ForecastBench | |
| HellaSwagnot in index | 89.2%#2 | Epoch AI Benchmarking Hub | |
| BIG-Bench Hardnot in index | 82.9%#4 | Epoch AI Benchmarking Hub | |
| WinoGrandenot in index | 89.2%#1 | Epoch AI Benchmarking Hub | |
| ARC (AI2 Challenge)not in index | 95.3%#1 | Epoch AI Benchmarking Hub | |
| PIQAnot in index | 85.9%#4 | Epoch AI Benchmarking Hub |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| WeirdML | 21.4%#141 | WeirdML | |
| Arena Coding | 1376#218 | Arena (LMArena) | |
| SWE-Bench Pro | 11.2%#21 | Scale AI SEAL | |
| SWE-Bench Pro (private)not in index | 11.2%#21 | Scale AI SEAL |
Agents & tools
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Cybench | 7.5%#18 | Cybench | |
| Terminal-Bench Hard | 6.8%#249 | Artificial Analysis | |
| τ²-Bench Telecom (AA)not in index | 19.0%#343 | Artificial Analysis | |
| TheAgentCompanynot in index | 7.4%#9 | TheAgentCompany |
Maths
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| OTIS Mock AIME | 9.7%#229 | Epoch AI Benchmarking Hub | |
| MATH Level 5 | 49.8%#54 | Epoch AI Benchmarking Hub | |
| Omni-MATH (HELM) | 24.9%#50 | HELM Capabilities | |
| Arena Maths | 1319#214 | Arena (LMArena) |
Knowledge
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-Omniscience | -17.1#230 | Artificial Analysis | |
| MMLU-Pro (HELM)not in index | 72.3%#35 | HELM Capabilities | |
| MMLUnot in index | 84.5%#11 | Epoch AI Benchmarking Hub | |
| TriviaQAnot in index | 82.7%#11 | Epoch AI Benchmarking Hub | |
| AA-Omniscience: accuracynot in index | 23.2%#263 | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | 47.6%#132 | Artificial Analysis |
Instruction following
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| IFBench | 39.0%#273 | Artificial Analysis | |
| IFEval (HELM) | 81.1%#43 | HELM Capabilities | |
| WildBench (HELM) | 78.3%#44 | HELM Capabilities | |
| Arena Instruction Followingnot in index | 1315#223 | Arena (LMArena) |
Human preference
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Text | 1336#220 | Arena (LMArena) | |
| Arena Creative Writingnot in index | 1305#212 | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1340#206 | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1329#228 | Arena (LMArena) |
Long context
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-LCR | 25.3%#411 | Artificial Analysis |
Composite
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Epoch Capabilities Indexnot in index | 128.8#151 | Epoch AI Benchmarking Hub | |
| AA Intelligence Index v4.3.2 | 7.3#484 | Artificial Analysis | |
| HELM Capabilities meannot in index | 61.8%#40 | HELM Capabilities |
Safety & honesty
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| FORTRESSnot in index | 20.6%#37 | Scale AI SEAL | |
| MASKnot in index | 61.4%#35 | Scale AI SEAL |
See also
Questions people ask
- What are Llama 3.1 405B's benchmark scores?
- As of 25 Oct 2026, Llama 3.1 405B scores 42.9 ±3.4 on the BenchLeader Index, strongest in knowledge (54) and weakest in coding (35). That rests on 20 independent benchmark results, and every score on this page links to its publisher.
- How does Llama 3.1 405B rank?
- Llama 3.1 405B is #580 of 785 ranked configurations on 25 Oct 2026. 285 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- When was Llama 3.1 405B released?
- Meta released Llama 3.1 405B on 23 Jul 2024.
Data as of 25 Oct 2026. Compare with another model.
Cite as: BenchLeader, “Llama 3.1 405B: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/llama-3-1-405b.