Model Release Radar
Price/capability frontier position, benchmark scores, and community signal
Model Release Radar
GPT-5.6 Terra
openai·closed weights·Proprietary·released Thursday, Jul 9, 2026
Frontier position
- Behind frontier DeepSWE pass@1 (agentic coding) - GPT-5.6 Luna, GLM-5.3-Flash, GPT-5.6 Sol 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) (xhigh effort, 95% CI 58.1%-62.3%, 4 runs) | 60.2% | $1.70 (median $1.49) | 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 | 52.8 |
| AA coding index | 70.6 |
| GPQA Diamond (science) | 90.8% |
| Humanity's Last Exam | 41.9% |
| IFBench (instruction following) | 66.3% |
| LCR | 75.0% |
| SciCode (coding) | 51.6% |
| Tau2 (tool use) | 80.4% |
| Tau2 (banking) | 29.7% |
| Terminal-Bench (hard) | 62.9% |
| Terminal-Bench 2.1 (agentic) | 80.1% |
Variants
This page covers 6 reasoning-effort variants of the same model.
| Variant | AA coding index | AA intelligence index | Price /1M |
|---|---|---|---|
| Extra-high effort (shown above) | 70.6 | 52.8 | $4.50/1M |
| High effort | 67.1 | 50.1 | $4.50/1M |
| Low effort | 58.1 | 41.3 | $4.50/1M |
| Max effort | 76.7 | 56.6 | $4.50/1M |
| Medium effort | 64.7 | 46.8 | $4.50/1M |
| Non-reasoning | 52.3 | 34.6 | $4.50/1M |
Community signal
| Variant | Coding Elo | Overall Elo | Votes |
|---|---|---|---|
| Extra-high effort | 1,487 | 1,447 | 22,345 |