Llama-3.1-Nemotron-70B-Instruct
Llama-3.1-Nemotron-70B-Instruct places in the top three on Stick to Your Role!.
15
Benchmarks with a score
0
Ranked first, out of five or more models
1
In the top three
NVIDIA Oct 2024 Llama-3.1-Nemotron-70B-Instruct
Open weights Flagship
No Epoch Capabilities Index score yet
- MicroVQA 44.2% #16 /19
- BigCodeBench-Hard 24.6% #50 /96
- U-MATH 42.5% #21 /30
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Arena-Hard-Auto | 84.9% | #5 of 38 | Official leaderboard | |
| Stick to Your Role! | 0.82 | #2 of 15 | Official leaderboard | |
| MuSR | 43.3% | #31 of 98 | Official leaderboard | |
| MMLU-Pro | 62.8% | #108 of 212 | Official leaderboard | |
| LMArena (Elo) | 1,299 | #232 of 335 | Official leaderboard | |
| LongBench v2 | 35.2% | #28 of 33 | Official leaderboard | |
| Arena-Hard v2.0 | 10.3% | #22 of 23 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| U-MATH | 42.5% | #21 of 30 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BigCodeBench-Hard | 24.6% | #50 of 96 | Official leaderboard | |
| BigCodeBench | 43.5% | #38 of 69 | Official leaderboard | |
| Aider-Edit | 54.9% | #30 of 34 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SnakeBench | 26 | #71 of 188 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BRIDGE | 42.8 | #27 of 39 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MicroVQA | 44.2% | #16 of 19 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Open LLM Leaderboard v2 | 36.9 | #9 of 99 | Official leaderboard |