Model Release Radar
Price/capability frontier position, benchmark scores, and community signal
Model Release Radar
GPT-5.5
openai·closed weights·Proprietary·released Thursday, Apr 23, 2026
Frontier position
- Behind frontier DeepSWE pass@1 (agentic coding) - Kimi K3, Grok 4.6, GPT-5.6 Sol, GLM-5.3, GPT-5.6 Terra 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 61.3%-67.5%, 4 runs) | 64.4% | $5.10 (median $4.58) | 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 | 54.7 |
| AA coding index | 71.6 |
| GPQA Diamond (science) | 93.2% |
| Humanity's Last Exam | 45.0% |
| IFBench (instruction following) | 71.6% |
| LCR | 79.0% |
| SciCode (coding) | 55.9% |
| Tau2 (tool use) | 93.0% |
| Tau2 (banking) | 36.7% |
| Terminal-Bench (hard) | 59.8% |
| Terminal-Bench 2.1 (agentic) | 79.4% |
Variants
This page covers 2 reasoning-effort variants of the same model.
| Variant | AA coding index | AA intelligence index | Price /1M |
|---|---|---|---|
| High effort (shown above) | 71.6 | 54.7 | $11.25/1M |
| Standard | 74.9 | 56.3 | $11.25/1M |
Community signal
| Variant | Coding Elo | Overall Elo | Votes |
|---|---|---|---|
| High effort | 1,495 | 1,471 | 61,604 |
| Standard | 1,481 | 1,466 | 62,975 |