whatmodel.sh / Grok 4.7
Grok 4.7
↗ share
+ contribute
Grok 4.7 is a closed-weights language model from SpaceXAI (xAI), released September 2026.
$ how it compares
The LLMs ranked either side of Grok 4.7, out of 828 with a score, then more from SpaceXAI (xAI).
| # | model | score | where | ||
|---|---|---|---|---|---|
| 45 |  Step 5 Preview | 75±1 | comparison only | ||
| 46 |  Claude Sonnet 5 | 75±1 | api $4.00/M | ||
| 47 | Grok 4.7 | 75±1 | api $3.00/M | ||
| 48 | Claude Opus 4.6 | 75±1 | api $10.00/M | ||
| 49 |  GPT-5.3-Codex | 74±1 | api $4.81/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 | ||
| 60 | Grok 4.20 Multi-Agent (0309) | 73±2 | api $1.56/M | ||
$ what it's good at
agent tasks▁▁▃▆█▆▅▅▅▄▃▁ #20 of 300 * · 12% of its score · 2 tests
Beats GPT-5.5, Hy4 preview (770B-A49B), GPT-5.6 Terra here, though they rank higher overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Arena Agent (October 2026 aggregate IPS) | 0.0404 IPS ✎ | ▁▁▁▄▂▃▇█▂▂▁▃ beats 35/49 | 11% |
| KlinikeBench strict pass@1 (333 interactive clinical encounters, Terminus-2) | 22.2% ✎ | ▁▁·▁▁▁▁▅▃█▅█ beats 21/27 | 1.4% |
coding▁▁▁▃▆██▇▆▄▃▁ #15 of 458 * · 9.5% of its score · 1 test
Beats GPT-5.6 Sol, GPT-5.5, MiMo-V2.6-Pro here, though they rank higher overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Arena WebDev (Code Arena) | 1637.5 ✎ | ▁▂▄▃▅█▄▇▆▄▁▁ beats 106/119 | 9.5% |
chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #60 of 393 * · 5.3% of its score · 1 test
Trails Gemma 4 31B, Gemini 2.5 Pro, Claude Sonnet 4.5 here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMArena (text) | 1442.5 ✎ | ▁▁▁▂▃▃▃▆▆▇█▃ beats 303/379 | 5.3% |
math▁▂▃▅▆▅▄█▄▁▁▁ #49 of 398 · 47% of its score · 3 tests
Trails A.X K2 (688B-A33B), DeepSeek V4 Flash (Preview, Apr 2026), GPT-5 here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| FrontierMath tiers 1–3 v2 | 53.0% ✎ | ▂··▁▁▃▄▄█▅▃▃ beats 37/82 | 25% |
| FrontierMath tier 4 v2 | 17.1% ✎ | ▁▂▁▂█▅▂▂▁▁▁▁ beats 16/63 | 20% |
| OTIS mock AIME 2024–2025 | 98.1% ✎ | ▃▃▄▃▃▃▇▇█▃▃▅ beats 172/193 | 1.1% |
other tests5 not in a task · 26% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Furniture Assembly (Epoch) | 20.8% ✎ | █▆▆▆▆▂▅▂▂▂·▅ beats 1/30 | 8.6% |
| Mystery Game Puzzles (Epoch) | 29.0% ✎ | █··▂▃▇▄█▂▃▁▁ beats 46/74 | 6.6% |
| Chess Puzzles (Epoch) | 38.0% ✎ | █▁▁▁▁▂▁▄▂▃▁▁ beats 114/135 | 4.3% |
| GPQA Diamond | 92.7% ✎ | ▁▁▁▁▂▄▆▄▅▇█▅ beats 191/208 | 4.3% |
| SimpleQA Verified | 56.0% ✎ | ▁▁▃▂▃▃▆▆█▃▂▅ beats 61/78 | 2.1% |
$ where to run it
Through an API
api · xAI · $3.00/M · $2 in / $6 out per 1M tokens · 500k context · docs.x.ai ↗ · price sourceStandard base token rate from models.dev. Provider-specific tiers, long-context surcharges, caching and promotions may differ.
$ how the score was worked out · Epoch AI — internal evaluatio… 73%, LMArena leaderboard dataset 26%, KlinikeBench: Evaluating Lang… 1%
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 | 8 | 73% |
 LMArena leaderboard dataset | 3 | 26% |
 KlinikeBench: Evaluating Language Models Beyond Diagnostic Accuracy (arXiv:2609.38480v2) | 1 | 1% |
| prior · pull toward the middle | 0% | |
| weighted average | = 74.7 |
$ 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