OpenAI·released 2026-02-051 source
GPT-5.3 Codex benchmark scores: 4 benchmarks tracked. 25% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 4 benchmarks·best result 79.3 on WeirdML (unverified)·1 of 4 independently reproduced·$1.75/$14 per M tokens
Consensus: LiteLLM · Cross-check: models.dev, OpenRouter · See every model’s pricing →
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| WeirdML | 79.3accuracy (%) | unverifiedT1 | 2026-02-05WeirdML Leaderboard |
| Terminal Bench | 78.43accuracy (%) | unverifiedT1 | 2026-02-05https://www.tbench.ai/leaderboard/terminal-bench/2.0 |
| SWE-Bench verified | 74.79accuracy (%) | reproduced· optimizedT1 | 2026-02-05Epoch AI |
| METR Time Horizons | 74.54accuracy (%) | unverifiedT2 | 2026-02-05 |
Claims drawn from cited facts, not live model generation.
This model comes from OpenAI and was released in 2026, placing its vintage in that release year.
2 cited facts
This model is scored on 4 tracked benchmarks, but it holds no current top score on any of them. Because its record has been independently reproduced, the reported scores are backed up by outside evaluation rather than resting on vendor claims alone.
3 cited facts
On average, this model trails the best benchmark score by 8.39 points under the disclosed harness, a moderate gap that reads as competitive but not front-of-pack rather than a capability statement. It holds the top score on 0 benchmarks, meaning there is no genuine category leadership yet.
2 cited facts
6 facts cross-checked across data sources: 2 corroborated, 2 single-source, 2 disputed.
Source facts, citations, and refresh stamp for this record.
Sources: epoch_benchmarks, litellm_prices, modelsdev_models, openrouter_models
GPT-5.3 Codex is an AI model developed by OpenAI, released 2026-02-05. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
GPT-5.3 Codex has recorded scores on 4 benchmarks, each shown with its evidence status.
GPT-5.3 Codex has recorded scores on 4 benchmarks — WeirdML, METR Time Horizons, SWE-Bench verified, Terminal Bench. The full table above shows each score with its evidence status.
1 of 4 recorded scores (25%) are independently reproduced rather than self-reported by the lab.
GPT-5.3 Codex has 4 tracked claims: 1 independently reproduced, 3 unverified.
Listed API pricing: $1.75 per million input tokens, $14 per million output tokens (prices disputed across sources). See the pricing block for the full breakdown.