gpt-5.6-sol-xhigh (codex-harness)
1,617±6
1,611CI1,623
aiqbench · LLM benchmarks
1,617±6
1,611CI1,623
1,522±6
1,515CI1,528
1,519±6
1,512CI1,525
One grid, every column. Pick axes in the Axes panel — one axis ranks like a single board, several blend into a weighted composite, all of them read as the index. Rank is assigned before any filter and never renumbers.
| Model | Org | ± CI | Swing | Add to compare | |||||
|---|---|---|---|---|---|---|---|---|---|
| 23 | gpt-5.6-sol-xhigh (codex-harness) | openai | Sep 2026 | $4 / $20 | 1,617 | 1,611–1,623 | #6–24 | ||
| 45 | gpt-5.6-terra-xhigh (codex-harness) | openai | Sep 2026 | $2 / $12 | 1,522 | 1,515–1,528 | #13–60 | ||
| 48 | GPT-5.6 Luna (xHigh, Codex Harness) | openai | Sep 2026 | $0.20 / $1.20 | 1,519 | 1,512–1,525 | #30–147 | ||
| 50 | gpt-5.5-xhigh (codex-harness) | openai | Sep 2026 | $5 / $30 | 1,513 | 1,507–1,519 | #9–34 | ||
| 62 | GPT-5.4 (High, Codex Harness) | openai | Sep 2026 | $2.50 / $15 | 1,464 | 1,445–1,483 | #12–27 | ||
| 78 | GPT-5 (Medium) | openai | Aug 2025 | $1.25 / $10 | 1,418 | 1,402–1,433 | #64–149 | ||
| 79 | GPT-5.2 | openai | Dec 2025 | $1.75 / $14 | 1,417 | 1,394–1,439 | #34–93 | ||
| 82 | GPT-5.3-Codex (Codex Harness) | openai | Oct 2026 | $1.75 / $14 | 1,407 | 1,393–1,420 | #29–236 | ||
| 87 | GPT-5.4 mini (High) | openai | Oct 2026 | $0.75 / $4.50 | 1,398 | 1,391–1,404 | #75–180 | ||
| 88 | GPT-5.1 (Medium) | openai | Nov 2025 | $1.25 / $10 | 1,396 | 1,384–1,407 | #45–242 | ||
| 110 | GPT-5.2-Codex | openai | Oct 2026 | $1.75 / $14 | 1,339 | 1,330–1,348 | #37–370 | ||
| 111 | GPT-5.1-Codex | openai | Oct 2026 | $1.25 / $10 | 1,337 | 1,325–1,349 | #53–375 | ||
| 124 | GPT-5.1-Codex-Mini | openai | Oct 2026 | $0.25 / $2 | 1,244 | 1,222–1,266 | #54–425 |
Showing WebDev Arena exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.