Model comparison
Llama 3.1-405B vs Mercury 2
Mercury 2 is the stronger model overall, scoring 39.1 to 30.7 on the Noometry Index.
Last verified . 12 shared benchmarks.
MetaSummary
- They share 12 benchmarks with published results for both. Llama 3.1-405B scores higher in 0 categories and Mercury 2 in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mercury 2 leads 53.8 to 38.9.
- The biggest single-benchmark swing is WeirdML: 21.4% for Llama 3.1-405B and 43.2% for Mercury 2.
- Llama 3.1-405B has downloadable open weights; the other is API-only.
Side by side
| Llama 3.1-405B | Mercury 2 | |
|---|---|---|
| Provider | Meta | Inception |
| Noometry Index | 30.7 | 39.1 |
| Released | 2024-07-23 | 2026-02-20 |
| Weights | Open | Proprietary |
| Context window | — | 128K |
| Max output | — | 50K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.75 |
| Results tracked | 42 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Llama 3.1-405B: 33.1 (#262), Mercury 2: 33.5 (#255)
| Benchmark | Llama 3.1-405B | Mercury 2 |
|---|---|---|
| WeirdML | 21.4% | 43.2% |
| LMArena Coding | 1291 | 1391 |
| LMArena WebDev | — | 1171 |
| SciCode | — | 38.7% |
| ALE-Bench | — | 785.58 |
Agentic & Tool Use Not comparable
Llama 3.1-405B: 21.0 (#140), Mercury 2: —
| Benchmark | Llama 3.1-405B | Mercury 2 |
|---|---|---|
| TheAgentCompany | 7.4% | — |
| Cybench | 7.5% | — |
Reasoning Mercury 2 leads
Llama 3.1-405B: 16.8 (#300), Mercury 2: 23.8 (#170)
| Benchmark | Llama 3.1-405B | Mercury 2 |
|---|---|---|
| LMArena Hard Prompts | 1269 | 1362 |
| SimpleBench | 23% | — |
| Kagi LLM Benchmark | 45% | — |
| CritPt | — | 0.8% |
| DTBench | 61.4% | — |
| BIG-Bench Hard | 82.9% | — |
| Epoch Capabilities Index | 128.75 | — |
| ForecastBench | 59.9 | — |
| HellaSwag | 89.2% | — |
| PIQA | 85.9% | — |
| WinoGrande | 89.2% | — |
Math Not comparable
Llama 3.1-405B: 18.4 (#290), Mercury 2: —
| Benchmark | Llama 3.1-405B | Mercury 2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 9.7% | — |
| Omni-MATH | 24.9% | — |
| LMArena Math | 1281 | — |
| MATH Level 5 | 49.8% | — |
Knowledge Mercury 2 leads
Llama 3.1-405B: 30.4 (#227), Mercury 2: 36.2 (#172)
| Benchmark | Llama 3.1-405B | Mercury 2 |
|---|---|---|
| LMArena Expert | 1243 | 1358 |
| GPQA Diamond | 50.9% | — |
| MMLU-Pro | 72.3% | — |
| Confabulations | 17.6% | — |
| Vectara Hallucination Rate | — | 12.3% |
| GPQA (HELM) | 52.2% | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 84.5% | — |
| TriviaQA | 82.7% | — |
Multilingual Mercury 2 leads
Llama 3.1-405B: 40.7 (#214), Mercury 2: 46.6 (#157)
| Benchmark | Llama 3.1-405B | Mercury 2 |
|---|---|---|
| LMArena Non-English | 1248 | 1331 |
| LMArena Chinese | 1242 | 1417 |
| LMArena Russian | 1265 | 1304 |
| LMArena French | 1279 | — |
| LMArena German | 1252 | — |
| LMArena Japanese | 1208 | — |
| LMArena Korean | 1184 | — |
| LMArena Spanish | 1260 | — |
Instruction Following Mercury 2 leads
Llama 3.1-405B: 65.9 (#214), Mercury 2: 70.2 (#165)
| Benchmark | Llama 3.1-405B | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1259 | 1329 |
| IFEval | 81.1% | — |
Long Context Mercury 2 leads
Llama 3.1-405B: 38.4 (#197), Mercury 2: 40.5 (#154)
| Benchmark | Llama 3.1-405B | Mercury 2 |
|---|---|---|
| LMArena Longer Query | 1266 | 1330 |
Writing & Preference Mercury 2 leads
Llama 3.1-405B: 38.9 (#251), Mercury 2: 53.8 (#155)
| Benchmark | Llama 3.1-405B | Mercury 2 |
|---|---|---|
| LMArena Text | 1284 | 1355 |
| LMArena Creative Writing | 1262 | 1289 |
| LMArena Multi-Turn | 1297 | 1358 |
| EQ-Bench Creative Writing | 870 | — |
| WildBench | 78.3% | — |
Frequently asked questions
Is Llama 3.1-405B better than Mercury 2?
Mercury 2 is the stronger model overall, scoring 39.1 to 30.7 on the Noometry Index.
Is Llama 3.1-405B or Mercury 2 better for coding?
They score almost the same on coding (33.1 vs 33.5); test both on your own repository before choosing.
How many benchmarks do Llama 3.1-405B and Mercury 2 share?
12 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and Mercury 2 has 17.