Benchmark
Arena ELO - Coding
Coding benchmarks compare models on programming tasks. Higher scores are better.
All coding benchmarksScores from LMArena data.
- Models measured
- 361
- Scores recorded
- 418
- Sources
- 1
- IQ weight
- 1.28
Score distribution
- 1,325
- Mean
- 1,374.5
- Median
- 162.1
- Std dev
- 1,081.6
- 10th percentile
- 1,488
- 90th percentile
- 682.8
- Min
This benchmark has a weight of 1.28 for chat models, measured over 361 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 401 | Gemma 2B IT· LMArena data | 1,009.5 |
| 402 | Llama 2 7B Chat· LMArena data | 1,001.8 |
| 403 | StripedHyena Nous 7B· LMArena data | 1,001 |
| 404 | Qwen1.5-4B-Chat· LMArena data | 998.7 |
| 405 | Guanaco 33B· LMArena data | 995.4 |
| 406 | PaLM 2· LMArena data | 994.4 |
| 407 | ChatGLM3 6B· LMArena data | 964.1 |
| 408 | Koala 13B· LMArena data | 944.8 |
| 409 | RWKV-4 Raven 14B· LMArena data | 927.8 |
| 410 | ChatGLM 6B· LMArena data | 919.3 |
| 411 | MPT 7B Chat· LMArena data | 913.1 |
| 412 | ChatGLM2 6B· LMArena data | 901.8 |
| 413 | OpenAssistant Pythia 12B· LMArena data | 900.2 |
| 414 | StableLM Tuned Alpha 7B· LMArena data | 885.9 |
| 415 | Alpaca 13B· LMArena data | 798.7 |
| 416 | Dolly 2.0 12B· LMArena data | 776.2 |
| 417 | FastChat-T5 3B· LMArena data | 763.8 |
| 418 | LLaMA 13B· LMArena data | 682.8 |
Showing 401–418 of 418 results.
Data credits: LMArena, CC BY 4.0 (licence)