whatmodel.sh / Grok 3 Preview (02-24)
Grok 3 Preview (02-24)
↗ share
+ contribute
Grok 3 Preview (02-24) is a closed-weights language model from SpaceXAI (xAI), released February 2025.
Catalogue identity notes
Comparison-only. Arena entry 'grok-3-preview-02-24' (text). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'grok-3-preview-02-24' as 'Grok-3-Preview-02-24' (xAI, Proprietary), linking https://x.ai/blog/grok-3. Released 2025-02: xAI 'Grok 3 Beta' post dated Feb 19, 2025. Dated pre-API Grok 3 snapshot (LMArena label 'Grok-3-Preview-02-24', link x.ai/blog/grok-3); kept separate from the later grok-3 API model, which xAI retired on May 15, 2026.
$ how it compares
The LLMs ranked either side of Grok 3 Preview (02-24), out of 1132 with a score, then more from SpaceXAI (xAI).
| # | model | score | where | ||
|---|---|---|---|---|---|
| 167 |  Nova 2 Omni (Preview) | 66±7 | api $0.93/M | ||
| 168 |  GPT-5.1-Codex | 66±2 | comparison only | ||
| 169 | Grok 3 Preview (02-24) | 66±3 | comparison only | ||
| 170 |  Llama-xLAM-2-70b-fc-r | 66±4 | local | ||
| 171 |  Qwen3.6 Flash | 66±1 | api $0.56/M | ||
| more from SpaceXAI (xAI) | |||||
| 30 | Grok 4.6 | 77±1 | api $3.00/M | ||
| 42 | Grok 4.5 | 75±1 | api $3.00/M | ||
| 47 | Grok 4.7 | 75±1 | api $3.00/M | ||
$ what it's good at
chat & writing▁▁▁▃▅▅▆█▆▆▆▂ #125 of 579 * · 95% of its score · 1 test
Beats LongCat 2.0 (1.6T-A48B), Inkling Small (266B-A12B), GPT-5.4 nano here, though they rank higher overall. Trails Mistral Large 3 (675B-A41B), Gemma 4 12B, Qwen3-VL 235B-A22B Instruct here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMArena (text) | 1411.4 ✎ | ▁▁▁▂▃▃▃▆▆▇█▃ beats 258/379 | 95% |
$ where to run it
No verified API or download recorded yet · add one
$ how the score was worked out · LMArena leaderboard dataset 95%
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 |
|---|---|---|
 LMArena leaderboard dataset | 1 | 95% |
| prior · pull toward the middle | 5% | |
| weighted average | = 66.3 |
$ 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