Model Release Radar
Price/capability frontier position, benchmark scores, and community signal
Model Release Radar
Claude Opus 5
anthropic·closed weights·Proprietary·released Friday, Jul 24, 2026
Frontier position
- On frontier DeepSWE pass@1 (agentic coding) - no tracked model currently beats it on both price and capability.
Cost vs. capability
Loading chart…
Benchmark scores
Measured cost per task (DeepSWE)
| Benchmark | Pass@1 | Measured cost / task | Frontier |
|---|---|---|---|
| DeepSWE (agentic coding) (max effort) | 73.7% | $11.84 | frontier |
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 | 61.5 |
| AA coding index | 76.5 |
| GPQA Diamond (science) | 93.7% |
| Humanity's Last Exam | 52.8% |
| LCR | 76.3% |
| SciCode (coding) | 54.3% |
| Tau2 (banking) | 44.7% |
| Terminal-Bench 2.1 (agentic) | 87.6% |
Variants
This page covers 5 reasoning-effort variants of the same model.
| Variant | AA coding index | AA intelligence index | Price /1M |
|---|---|---|---|
| High effort (shown above) | 76.5 | 61.5 | $10/1M |
| Extra-high effort | 77.0 | 62.5 | $10/1M |
| Low effort | 66.9 | 52.5 | $10/1M |
| Max effort | 78.0 | 63.1 | $10/1M |
| Medium effort | 74.3 | 58.6 | $10/1M |
Community signal
| Variant | Coding Elo | Overall Elo | Votes |
|---|---|---|---|
| High effort | 1,531 | 1,504 | 31,570 |
| Max effort | 1,528 | 1,505 | 15,398 |