whatmodel.sh / Llama2 70B SteerLM Chat
Llama2 70B SteerLM Chat
↗ share
+ contribute
Llama2 70B SteerLM Chat is an open-weights language model from NVIDIA, released November 2023. Its published size is 70B parameters. Licence: llama2.
Catalogue identity notes
Comparison-only. Arena entry 'llama2-70b-steerlm-chat' (text). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'llama2-70b-steerlm-chat' as 'NV-Llama2-70B-SteerLM-Chat' (Nvidia, Llama 2 Community), linking https://huggingface.co/nvidia/Llama2-70B-SteerLM-Chat. Maker repo nvidia/Llama2-70B-SteerLM-Chat @03837fd: licence tag llama2. Parameters: card: 'a 70 billion parameter generative language model'. Released 2023-11: month the maker's Hugging Face repo was created (createdAt 2023-11-22).
$ how it compares
The LLMs ranked either side of Llama2 70B SteerLM Chat, out of 1132 with a score, then more from NVIDIA.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 887 |  Mistral 7B Instruct v0.3 | 39±1 | local | ||
| 888 |  Vicuna 33B v1.3 | 39±1 | local | ||
| 889 | Llama2 70B SteerLM Chat | 39±2 | comparison only | ||
| 890 |  DeepSeek-Coder 6.7B Base | 39±1 | local | ||
| 891 |  Starling-LM 7B alpha | 39±1 | local | ||
| more from NVIDIA | |||||
| 109 | Nemotron 3 Ultra 550B-A55B | 69±1 | api $1.35/M +local | ||
| 182 | Nemotron Cascade 2 30B-A3B | 66±1 | local | ||
| 198 | Nemotron 3 Super 120B-A12B | 65±1 | api $0.28/M +local | ||
$ what it's good at
chat & writing▁▁▁▃▅▅▆█▆▆▆▂ #500 of 579 * · 98% of its score · 2 tests
Beats Gemma 4 E2B, Code Llama 70B Instruct, QwQ-32B-Preview here, though they rank higher overall. Trails Granite 4.0 H 350M, LFM2 350M, Gemma 3 1B here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Polyrating rating (bias-aware re-fit of Chatbot Arena votes, mid-2024) | 1111.0 ✎ | ▂▁▂▁▃▇█▆▇▄▂▂ beats 53/95 | 49% |
| LMArena (text) | 1154.7 ✎ | ▁▁▁▂▃▃▃▆▆▇█▃ beats 44/379 | 48% |
$ where to run it
No verified API or download recorded yet · add one
Official weights and documentation: huggingface.co/nvidia ↗
$ how the score was worked out · Polyrating: A Cost-Effective… 49%, LMArena leaderboard dataset 48%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3) | 1 | 49% |
 LMArena leaderboard dataset | 1 | 48% |
| prior · pull toward the middle | 2% | |
| weighted average | = 39.1 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json