Model comparison
GPT-5.5 vs GPT-5-Codex
GPT-5.5 is the stronger model overall, scoring 63.4 to 37.9 on the Noometry Index. GPT-5-Codex costs 3.3× less per token, which makes it the better buy when GPT-5.5's lead doesn't matter for your workload.
Last verified . 3 shared benchmarks.
Summary
- They share 3 benchmarks with published results for both. GPT-5.5 scores higher in 3 categories and GPT-5-Codex in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.5 leads 72.8 to 30.9.
- The biggest single-benchmark swing is Terminal-Bench: 84.7% for GPT-5.5 and 44.3% for GPT-5-Codex.
- GPT-5-Codex is cheaper at $1.25 / $10 per million input/output tokens, against $5 / $30 for GPT-5.5.
- GPT-5.5 accepts more context: 1.05M tokens versus 400K.
Side by side
| GPT-5.5 | GPT-5-Codex | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 63.4 | 37.9 |
| Released | 2026-04-23 | 2025-09-15 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 400K |
| Max output | 128K | 128K |
| Input $ / M tokens | $5 | $1.25 |
| Output $ / M tokens | $30 | $10 |
| Results tracked | 71 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.5 leads
GPT-5.5: 58.2 (#17), GPT-5-Codex: 42.4 (#103)
| Benchmark | GPT-5.5 | GPT-5-Codex |
|---|---|---|
| WeirdML | 84.9% | 54.5% |
| SWE-bench Verified | 80.6% | — |
| DeepSWE | 67% | — |
| FrontierCode | 43% | — |
| LMArena WebDev | 1513 | — |
| SciCode | 56.1% | — |
| GSO | 40.2% | — |
| LMArena Coding | 1494 | — |
| MirrorCode | 10% | — |
| ALE-Bench | 1,943 | — |
Agentic & Tool Use GPT-5.5 leads
GPT-5.5: 50.7 (#6), GPT-5-Codex: 31.0 (#72)
| Benchmark | GPT-5.5 | GPT-5-Codex |
|---|---|---|
| Terminal-Bench | 84.7% | 44.3% |
| APEX-Agents | 55.1% | — |
| OSWorld 2.0 | 13% | — |
| Remote Labor Index | 6.3% | — |
| τ²-bench Banking | 44.6% | — |
| DeepResearch Bench | 54% | — |
| PostTrainBench | 27.2% | — |
| ExploitBench | 47.4% | — |
| GBAEval | 53.2% | — |
| GDP.pdf | 26% | — |
| LMArena Search | 1242 | — |
| Vending-Bench 2 | 7,524 | — |
Reasoning GPT-5.5 leads
GPT-5.5: 72.8 (#11), GPT-5-Codex: 30.9 (#83)
| Benchmark | GPT-5.5 | GPT-5-Codex |
|---|---|---|
| Kagi LLM Benchmark | 88.8% | 70.3% |
| ARC-AGI-2 | 85% | — |
| SimpleBench | 69% | — |
| NYT Connections (extended) | 96.2% | — |
| ARC-AGI-1 | 95% | — |
| CritPt | 27.1% | — |
| Chess Puzzles | 54% | — |
| EBR-Bench | 34.3% | — |
| LMArena Hard Prompts | 1489 | — |
| Mystery Game Puzzles | 56% | — |
| DTBench | 96% | — |
| LMCA | 54.3% | — |
| Surface Evolver Bench | 88.1% | — |
| Bench to the Future 3 | 0.14 | — |
| Epoch Capabilities Index | 159.1 | — |
| ForecastBench | 60.6 | — |
Math Not comparable
GPT-5.5: 81.7 (#11), GPT-5-Codex: —
| Benchmark | GPT-5.5 | GPT-5-Codex |
|---|---|---|
| FrontierMath (Tiers 1-3) | 85.3% | — |
| FrontierMath Tier 4 | 72.5% | — |
| MathArena Final-Answer Competitions | 94.3% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| ProofBench | 50% | — |
| LMArena Math | 1486 | — |
| FrontierMath (Feb 2025 set) | 51.7% | — |
| FrontierMath Erdős | 0% | — |
| FrontierMath Tier 4 (v1) | 35.4% | — |
Knowledge Not comparable
GPT-5.5: 64.4 (#17), GPT-5-Codex: —
| Benchmark | GPT-5.5 | GPT-5-Codex |
|---|---|---|
| GPQA Diamond | 94% | — |
| SimpleQA Verified | 63% | — |
| Vectara Hallucination Rate | 9.3% | — |
| LMArena Expert | 1508 | — |
Multimodal Not comparable
GPT-5.5: 46.9 (#12), GPT-5-Codex: —
| Benchmark | GPT-5.5 | GPT-5-Codex |
|---|---|---|
| LMArena Vision | 1297 | — |
| Blueprint-Bench 2 | 36.2% | — |
| Furniture Assembly | 44.2% | — |
| LMArena Document | 1486 | — |
Multilingual Not comparable
GPT-5.5: 56.4 (#20), GPT-5-Codex: —
| Benchmark | GPT-5.5 | GPT-5-Codex |
|---|---|---|
| LMArena Non-English | 1467 | — |
| LMArena Chinese | 1533 | — |
| LMArena French | 1486 | — |
| LMArena German | 1480 | — |
| LMArena Japanese | 1498 | — |
| LMArena Korean | 1460 | — |
| LMArena Russian | 1473 | — |
| LMArena Spanish | 1468 | — |
Instruction Following Not comparable
GPT-5.5: 77.5 (#18), GPT-5-Codex: —
| Benchmark | GPT-5.5 | GPT-5-Codex |
|---|---|---|
| LMArena Instruction Following | 1479 | — |
Long Context Not comparable
GPT-5.5: 48.3 (#12), GPT-5-Codex: —
| Benchmark | GPT-5.5 | GPT-5-Codex |
|---|---|---|
| CL-bench Life | 22.2% | — |
| LMArena Longer Query | 1484 | — |
Writing & Preference Not comparable
GPT-5.5: 72.7 (#13), GPT-5-Codex: —
| Benchmark | GPT-5.5 | GPT-5-Codex |
|---|---|---|
| LMArena Text | 1472 | — |
| LMArena Creative Writing | 1455 | — |
| EQ-Bench Creative Writing | 1844 | — |
| EQ-Bench 4 | 1315 | — |
| LMArena Multi-Turn | 1476 | — |
Frequently asked questions
Is GPT-5.5 better than GPT-5-Codex?
GPT-5.5 is the stronger model overall, scoring 63.4 to 37.9 on the Noometry Index. GPT-5-Codex costs 3.3× less per token, which makes it the better buy when GPT-5.5's lead doesn't matter for your workload.
Which is cheaper, GPT-5.5 or GPT-5-Codex?
GPT-5-Codex is cheaper. It lists at $1.25 per million input tokens and $10 per million output tokens; GPT-5.5 lists at $5 and $30.
Is GPT-5.5 or GPT-5-Codex better for coding?
GPT-5.5 scores higher on coding benchmarks: 58.2 versus 42.4 in the Noometry coding category.
Which has the bigger context window?
GPT-5.5 does, with 1.05M tokens against 400K.
How many benchmarks do GPT-5.5 and GPT-5-Codex share?
3 benchmarks have published results for both models. GPT-5.5 has 71 scored results on Noometry and GPT-5-Codex has 3.