Model comparison
Llama 3.1-70B vs Mercury
Mercury is the stronger model overall, scoring 37.6 to 29.6 on the Noometry Index.
Last verified . 8 shared benchmarks.
MetaSummary
- They share 8 benchmarks with published results for both. Llama 3.1-70B scores higher in 2 categories and Mercury in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mercury leads 46.2 to 35.4.
- Llama 3.1-70B has downloadable open weights; the other is API-only.
Side by side
| Llama 3.1-70B | Mercury | |
|---|---|---|
| Provider | Meta | Inception |
| Noometry Index | 29.6 | 37.6 |
| Released | 2024-07-23 | — |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.40 | — |
| Output $ / M tokens | $0.40 | — |
| Results tracked | 35 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mercury leads
Llama 3.1-70B: 30.3 (#296), Mercury: 38.7 (#170)
| Benchmark | Llama 3.1-70B | Mercury |
|---|---|---|
| LMArena Coding | 1260 | 1322 |
| WeirdML | 9% | — |
| BigCodeBench Instruct | 46.1% | — |
| BigCodeBench Complete | 54.8% | — |
Agentic & Tool Use Not comparable
Llama 3.1-70B: 25.1 (#112), Mercury: —
| Benchmark | Llama 3.1-70B | Mercury |
|---|---|---|
| TheAgentCompany | 6.9% | — |
| BALROG | 27.9% | — |
Reasoning Llama 3.1-70B leads
Llama 3.1-70B: 21.6 (#220), Mercury: 17.5 (#293)
| Benchmark | Llama 3.1-70B | Mercury |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1285 |
| Kagi LLM Benchmark | — | 21.6% |
| DTBench | 60% | — |
| LMCA | 14.8% | — |
| Epoch Capabilities Index | 125.92 | — |
Math Not comparable
Llama 3.1-70B: 13.5 (#304), Mercury: —
| Benchmark | Llama 3.1-70B | Mercury |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 3.6% | — |
| Omni-MATH | 21% | — |
| LMArena Math | 1252 | — |
| MATH Level 5 | 36.7% | — |
Knowledge Not comparable
Llama 3.1-70B: 24.2 (#269), Mercury: —
| Benchmark | Llama 3.1-70B | Mercury |
|---|---|---|
| GPQA Diamond | 44.2% | — |
| MMLU-Pro | 65.3% | — |
| GPQA (HELM) | 42.6% | — |
| LMArena Expert | 1209 | — |
| MMLU | 80.1% | — |
Multilingual Mercury leads
Llama 3.1-70B: 38.8 (#225), Mercury: 41.6 (#206)
| Benchmark | Llama 3.1-70B | Mercury |
|---|---|---|
| LMArena Non-English | 1219 | 1260 |
| LMArena Chinese | 1215 | — |
| LMArena French | 1261 | — |
| LMArena German | 1222 | — |
| LMArena Japanese | 1132 | — |
| LMArena Korean | 1140 | — |
| LMArena Russian | 1234 | — |
| LMArena Spanish | 1253 | — |
Instruction Following Too close to call
Llama 3.1-70B: 65.3 (#223), Mercury: 65.2 (#224)
| Benchmark | Llama 3.1-70B | Mercury |
|---|---|---|
| LMArena Instruction Following | 1231 | 1239 |
| IFEval | 82.1% | — |
Long Context Too close to call
Llama 3.1-70B: 37.6 (#214), Mercury: 38.4 (#198)
| Benchmark | Llama 3.1-70B | Mercury |
|---|---|---|
| LMArena Longer Query | 1241 | 1266 |
Writing & Preference Mercury leads
Llama 3.1-70B: 35.4 (#267), Mercury: 46.2 (#221)
| Benchmark | Llama 3.1-70B | Mercury |
|---|---|---|
| LMArena Text | 1261 | 1282 |
| LMArena Creative Writing | 1232 | 1191 |
| LMArena Multi-Turn | 1256 | 1282 |
| EQ-Bench Creative Writing | 784 | — |
| WildBench | 75.8% | — |
Frequently asked questions
Is Llama 3.1-70B better than Mercury?
Mercury is the stronger model overall, scoring 37.6 to 29.6 on the Noometry Index.
Is Llama 3.1-70B or Mercury better for coding?
Mercury scores higher on coding benchmarks: 38.7 versus 30.3 in the Noometry coding category.
How many benchmarks do Llama 3.1-70B and Mercury share?
8 benchmarks have published results for both models. Llama 3.1-70B has 35 scored results on Noometry and Mercury has 9.