whatmodel.sh / Grok 3 Beta
Grok 3 Beta
↗ share
+ contribute
Grok 3 Beta is a closed-weights language model from SpaceXAI (xAI), released April 2025. Licence: proprietary.
Catalogue identity notes
Comparison model from the Epoch AI internal-evaluation CSVs (Epoch release date 2025-04-09). API model grok-3-beta; distinct from arena's 'grok-3-preview-02-24'. Not listed on xAI's current models page (observed 2026-09-28).
$ how it compares
The LLMs ranked either side of Grok 3 Beta, out of 828 with a score, then more from SpaceXAI (xAI).
| # | model | score | where | ||
|---|---|---|---|---|---|
| 185 | Grok 3 Mini Beta | 64±1 | comparison only | ||
| 186 |  MiniCPM5 2B | 64±1 | local | ||
| 187 | Grok 3 Beta | 63±1 | comparison only | ||
| 188 |  Qwen3-Next 80B-A3B Thinking | 63±1 | api $0.41/M +local | ||
| 189 |  DeepSeek R1 (Jan '25) | 63±1 | api $4.00/M +local | ||
| 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
agent tasks▁▁▂▆█▆▅▄▄▃▂▁ #216 of 340 * · 11% of its score · 2 tests
Beats o1 (2024-12-17), o3-mini here, though they rank higher overall. Trails SmolLM3 3B, Jamba 1.5 Mini, Mellum2 12B-A2.5B Instruct here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Finance Agent Benchmark v1 (537 questions, class-balanced accuracy) | 25.8% ✎ | █·▃▃·█▅▅▅▅▃▅ beats 13/18 | 8.5% |
| BFCL v3 | 63.3% ✎ | ▁▁▁▁▁▃▅█▅▄▁▁ beats 89/114 | 2.3% |
coding▁▁▁▃▅▇█▇▅▄▃▁ #155 of 524 * · 39% of its score · 2 tests
Beats Qwen3.5 Plus, Gemini 2.5 Pro, Gemini 3.1 Flash-Lite here, though they rank higher overall. Trails Devstral Small 2 24B, Llama 3.1 Nemotron Ultra 253B v1, Nemotron 3.5 Lightning 30B-A3B here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Aider polyglot (225 exercises, two attempts) | 53.3% ✎ | ▂·▂▃▅▂▃█▆▄▂▂ beats 29/49 | 33% |
| WebApp1K-Duo-React pass@1 (onekq-ai) | 60.2% ✎ | ▁··▁·▁▁▁▆█▇█ beats 14/45 | 5.6% |
math▁▂▃▅▇▅▅█▄▁▁▁ #182 of 462 * · 24% of its score · 2 tests
Beats MiniMax-M2.1, Mistral Medium 3.5 (128B) here, though they rank higher overall. Trails Olmo 3 7B Think, Nemotron Nano 9B v2, Qwen3-VL 4B Thinking here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| MATH level 5 | 88.7% ✎ | ▂▂▅▆▄█▆▃▅▂▃▄ beats 76/92 | 13% |
| OTIS mock AIME 2024–2025 | 55.6% ✎ | ▃▃▄▃▃▃▇▇█▃▂▅ beats 82/193 | 11% |
web search▂·▂▇▅█▃▄▁▃▁▁ #6 of 92 * · 8.5% of its score · 1 test
Beats GPT-6 Astra, Claude Opus 5.5, Claude Fable 5.1 here, though they rank higher overall. Trails GPT-4.1 here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Finance Agent Benchmark v1 (537 questions, class-balanced accuracy) | 25.8% ✎ | █·▃▃·█▅▅▅▅▃▅ beats 13/18 | 8.5% |
other tests2 not in a task · 27% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| GPQA Diamond | 75.8% ✎ | ▁▁▁▁▂▄▆▄▅▇█▅ beats 114/208 | 20% |
| EQ-Bench 3 (emotional intelligence, judge Elo) | 1176.6 ✎ | ▁·▂▁▄▅▅▃█▄▁▁ beats 28/62 | 6.9% |
$ where to run it
No verified API or download recorded yet · add one
$ how the score was worked out · Epoch AI — internal evaluatio… 43%, Aider polyglot benchmark runs 33%, Finance Agent Benchmark (Vals… 8% and 3 more
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 |
|---|---|---|
 Epoch AI — internal evaluations | 3 | 43% |
 Aider polyglot benchmark runs | 1 | 33% |
 Finance Agent Benchmark (Vals AI, arXiv:2508.00828v1) | 1 | 8% |
 EQ-Bench 3 canonical leaderboard results | 1 | 7% |
| WebApp1K models leaderboard (onekq-ai) | 1 | 6% |
| Berkeley Function Calling Leaderboard result archive | 1 | 2% |
| prior · pull toward the middle | 1% | |
| weighted average | = 63.4 |
$ 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