Model Release Radar
Price/capability frontier position, benchmark scores, and community signal
Model Release Radar
Grok 4.5
xai·closed weights·Proprietary·released Wednesday, Jul 8, 2026
Frontier position
- Behind frontier DeepSWE pass@1 (agentic coding) - Gemini 3.7 Flash, GPT-5.6 Terra, Claude Opus 5, GPT-5.6 Sol, GPT-5.6 Luna are priced the same or lower and at least as capable.
Cost vs. capability
Loading chart…
Benchmark scores
Measured cost per task (DeepSWE)
| Benchmark | Pass@1 | Measured cost / task | Frontier |
|---|---|---|---|
| DeepSWE (agentic coding) (high effort, 95% CI 51.5%-56.0%, 4 runs) | 53.8% | $2.42 (median $2.02) | behind |
Artificial Analysis scores (no matched cost)
Artificial Analysis scores below have no measured per-task cost, so no frontier claim is made for them here.
| Benchmark | Score |
|---|---|
| AA intelligence index | 55.8 |
| AA coding index | 72.4 |
| GPQA Diamond (science) | 93.1% |
| Humanity's Last Exam | 42.7% |
| LCR | 74.0% |
| SciCode (coding) | 54.1% |
| Tau2 (banking) | 42.1% |
| Terminal-Bench 2.1 (agentic) | 81.6% |
Community signal
| Variant | Coding Elo | Overall Elo | Votes |
|---|---|---|---|
| Rating | 1,483 | 1,451 | 24,152 |