Coding-specialised.
| Benchmark | Score | Δ vs prior | Rank (current) | Configuration | Source |
|---|---|---|---|---|---|
SWE-bench Verified | 85% | #2 of 9 | leaderboard | benchlm.ai ↗ | |
τ²-bench (Telecom) | 86% | #6 of 10 | leaderboard | benchlm.ai ↗ | |
Artificial Analysis Intelligence Index | 44.3 | #4 of 11 | leaderboard | benchlm.ai ↗ |
| Version | Released | $ in / out | Terminal-Bench | SWE-bench | GPQA | HLE | ARC-AGI-2 | τ²-bench |
|---|---|---|---|---|---|---|---|---|
| GPT-4o | $2.5 / $10 | — | — | — | — | — | 25.1% | |
| o1 | $15 / $60 | — | — | — | — | — | 62.6% | |
| o3-mini | $1.1 / $4.4 | — | 49.3% | — | — | — | 28.7% | |
| GPT-4.1 | $2 / $8 | — | 54.6% | — | — | — | 47.1% | |
| o3 | $2 / $8 | — | 69.1% | — | — | — | 80.7% | |
| GPT-5 | $1.25 / $10 | — | 74.9% | 85.7% | — | — | 84.8% | |
| GPT-5.1 | $1.25 / $10 | — | — | — | — | — | 81.9% | |
| GPT-5.2 | $1.75 / $14 | — | 80% | — | — | 52.9% | 84.8% | |
| GPT-5.3 Codex | $1.75 / $14 | — | 85% | — | — | — | 86% | |
| GPT-5.4 | $2.5 / $15 | — | — | 92.8% | 39.8% | 73.3% | 98.9% | |
| GPT-5.5 | $5 / $30 | 76.4% | — | 93.6% | 41.4% | 85% | 98% | |
| GPT-5.5 Pro | $30 / $180 | — | — | — | 43.1% | 84.2% | — | |
| GPT-5.6 Luna | $0.2 / $1.2 | 79% | — | 92.3% | — | 59.5% | — | |
| GPT-5.6 Sol | $5 / $30 | 85.8% | — | 94.6% | — | 92.5% | 85.1% | |
| GPT-5.6 Terra | $2 / $12 | 77.5% | — | 92.9% | — | 83.9% | 86.3% | |
| GPT-6 Astra | $10 / $50 | 87.3% | — | 96% | 57.2% | 95% | — | |
| GPT-6 Luna | $0.1 / $0.5 | 73% | — | — | — | 59.3% | — | |
| GPT-6 Sol | $2 / $10 | 83.1% | — | — | — | 89.6% | — | |
| GPT-6.1 Sol | $2 / $10 | — | — | — | — | 94.2% | — |