whatmodel.sh / Grok 4 (0709)
Grok 4 (0709)
↗ share
+ contribute
Grok 4 (0709) is a closed-weights language model from SpaceXAI (xAI), released July 2025. Licence: proprietary.
Catalogue identity notes
Comparison model from the Epoch AI internal-evaluation CSVs (Epoch release date 2025-07-09). Dated API model grok-4-0709; distinct from grok-4-1-fast-reasoning, grok-4-20 and later. Not listed on xAI's current models page (observed 2026-09-28). Epoch's gpqa/otis rows for this version have no run start time or logs and rounded values, so only the chess run is used.
$ how it compares
The LLMs ranked either side of Grok 4 (0709), out of 828 with a score, then more from SpaceXAI (xAI).
| # | model | score | where | ||
|---|---|---|---|---|---|
| 117 |  MiMo-V2-Omni | 68±2 | comparison only | ||
| 118 |  Gemini 2.5 Pro Experimental (03-25) | 68±3 | comparison only | ||
| 119 | Grok 4 (0709) | 68±1 | comparison only | ||
| 120 |  MiniMax-M2.7 | 68±1 | api $0.53/M +local | ||
| 121 |  Qwen3.6 35B-A3B | 68±1 | api $0.31/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▁▁▂▆█▆▅▄▄▃▂▁ #138 of 340 * · 8.4% of its score · 2 tests
Beats o3 here, though they rank higher overall. Trails SmolLM3 3B, Jamba 1.5 Large, MiniCPM5 2B here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| BFCL V4 (December 2025 archive) | 61.4% ✎ | ▁▁▁▂██▅▅▆▃▂▂ beats 71/77 | 5.8% |
| Galileo Agent Leaderboard v2 (action completion) | 42.0% ✎ | ▅▃·▃▃▅▅█▃█▅▅ beats 9/19 | 2.5% |
coding▁▁▁▃▅▇█▇▅▄▃▁ #91 of 524 * · 28% of its score · 1 test
Beats Grok 4.20 (0309 reasoning), GPT-5.4 mini, GPT-5.1 here, though they rank higher overall. Trails Llama 3.1 Nemotron Ultra 253B v1 here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Aider polyglot (225 exercises, two attempts) | 79.6% ✎ | ▂·▂▃▅▂▃█▆▄▃▂ beats 45/49 | 28% |
chat & writing▁▁▁▃▅▄▆█▇▇▇▃ #110 of 463 * · 12% 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) | 1410.8 ✎ | ▁▁▁▂▃▃▃▆▆▇█▃ beats 256/379 | 12% |
math▁▂▃▅▇▅▅█▄▁▁▁ #103 of 462 * · 7.6% of its score · 1 test
Beats Claude Sonnet 4.6, MiniMax-M3, Nemotron 3 Ultra 550B-A55B here, though they rank higher overall. Trails Gemini 2.5 Flash, GLM-4.5-Air, Granite 4.2 30B here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| OTIS mock AIME 2024–2025 | 84.0% ✎ | ▃▃▄▃▃▃▇▇█▃▂▅ beats 122/193 | 7.6% |
vision & documents▁▁▃▃▂▃▅▄▇▇█▃ #100 of 182 * · 8.3% of its score · 1 test
Beats DeepSeek V4 Flash Vision (Exp) here, though they rank higher overall. Trails GPT-4.1 mini, Qwen3.5 4B, Gemini 2.5 Flash here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Arena vision (style controlled) | 1184.2 ✎ | ▁▁▂▂▂▂▄▅▅▆██ beats 62/145 | 8.3% |
web search▂·▂▇▅█▃▄▁▂▁▁ #81 of 92 * · 4.9% of its score · 1 test
Beats Nemotron 3 Ultra 550B-A55B here, though they rank higher overall. Trails GPT-4.1 nano, GPT-4o mini (2024-07-18), Mistral Small 3.1 24B (2503) here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Arena search systems (style controlled) | 1121.5 ✎ | ▁·▃▁▂▂▂█▅▂▁▁ beats 1/30 | 4.9% |
other tests4 not in a task · 30% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| GPQA Diamond | 87.0% ✎ | ▁▁▁▁▂▄▆▄▅▇█▅ beats 155/208 | 17% |
| EQ-Bench 3 (emotional intelligence, judge Elo) | 1190.3 ✎ | ▁·▂▁▄▅▅▃█▄▁▁ beats 29/62 | 7.4% |
| Chess Puzzles (Epoch) | 28.0% ✎ | █▁▁▁▁▂▁▄▃▂▁▁ beats 101/135 | 5.3% |
| Vectara hallucination leaderboard, 2025 dataset (HHEM-2.3, factual consistency rate) | 95.2% ✎ | ▁▁▂▃▄▄█▆▃▂▂▁ beats 63/140 | 0.3% |
$ where to run it
No verified API or download recorded yet · add one
$ how the score was worked out · Epoch AI — internal evaluatio… 30%, Aider polyglot benchmark runs 28%, LMArena leaderboard dataset 25% and 4 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 | 30% |
 Aider polyglot benchmark runs | 1 | 28% |
 LMArena leaderboard dataset | 3 | 25% |
 EQ-Bench 3 canonical leaderboard results | 1 | 7% |
| Berkeley Function Calling Leaderboard result archive | 1 | 6% |
| Galileo Agent Leaderboard (v1 and v2 results) | 1 | 3% |
| Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository) | 1 | 0% |
| prior · pull toward the middle | 1% | |
| weighted average | = 68.0 |
$ 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