Model comparison
GPT-5.2 Codex vs GPT-6 Astra
GPT-6 Astra is the stronger model overall, scoring 70.3 to 42.2 on the Noometry Index. GPT-5.2 Codex costs 4.2× less per token, which makes it the better buy when GPT-6 Astra's lead doesn't matter for your workload.
Last verified . 2 shared benchmarks.
Summary
- They share 2 benchmarks with published results for both. GPT-5.2 Codex scores higher in 0 categories and GPT-6 Astra in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where GPT-6 Astra leads 70.5 to 45.4.
- GPT-5.2 Codex is cheaper at $1.75 / $14 per million input/output tokens, against $10 / $50 for GPT-6 Astra.
- GPT-6 Astra accepts more context: 1.05M tokens versus 400K.
Side by side
| GPT-5.2 Codex | GPT-6 Astra | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 42.2 | 70.3 |
| Released | 2025-12-18 | 2026-09-03 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 1.05M |
| Max output | 128K | 128K |
| Input $ / M tokens | $1.75 | $10 |
| Output $ / M tokens | $14 | $50 |
| Results tracked | 5 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Astra leads
GPT-5.2 Codex: 45.4 (#66), GPT-6 Astra: 70.5 (#3)
| Benchmark | GPT-5.2 Codex | GPT-6 Astra |
|---|---|---|
| LMArena WebDev | 1339 | 1792 |
| ALE-Bench | 1,300 | 2,951 |
| DeepSWE | — | 74.1% |
| FrontierCode | — | 53.3% |
| SWE-bench Verified (bash only) | 72.8% | — |
| SWE-bench Multilingual | 66.3% | — |
| FrontierSWE | — | 65.5% |
| SciCode | — | 56.5% |
| WeirdML | — | 93.6% |
| LMArena Coding | — | 1488 |
| MirrorCode | — | 46.7% |
Agentic & Tool Use GPT-6 Astra leads
GPT-5.2 Codex: 40.7 (#20), GPT-6 Astra: 52.3 (#3)
| Benchmark | GPT-5.2 Codex | GPT-6 Astra |
|---|---|---|
| Terminal-Bench | 66.5% | — |
| APEX-Agents | — | 64.7% |
| Remote Labor Index | — | 20.8% |
| BALROG | — | 68.3% |
| Vending-Bench 2 | — | 15,515 |
Reasoning Not comparable
GPT-5.2 Codex: —, GPT-6 Astra: 85.1 (#1)
| Benchmark | GPT-5.2 Codex | GPT-6 Astra |
|---|---|---|
| ARC-AGI-2 | — | 95% |
| NYT Connections (extended) | — | 98.1% |
| ARC-AGI-1 | — | 98.5% |
| CritPt | — | 31.7% |
| Chess Puzzles | — | 72% |
| EBR-Bench | — | 76.2% |
| LMArena Hard Prompts | — | 1464 |
| Mystery Game Puzzles | — | 84% |
| DTBench | — | 97.3% |
| LMCA | — | 64.4% |
| Bench to the Future 3 | — | 0.14 |
| Epoch Capabilities Index | — | 166.6 |
Math Not comparable
GPT-5.2 Codex: —, GPT-6 Astra: 93.4 (#1)
| Benchmark | GPT-5.2 Codex | GPT-6 Astra |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 93.7% |
| FrontierMath Tier 4 | — | 97.6% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 99% |
| LMArena Math | — | 1463 |
| FrontierMath Erdős | — | 2.9% |
Knowledge Not comparable
GPT-5.2 Codex: —, GPT-6 Astra: 75.3 (#1)
| Benchmark | GPT-5.2 Codex | GPT-6 Astra |
|---|---|---|
| GPQA Diamond | — | 95.8% |
| Humanity's Last Exam | — | 54.8% |
| SimpleQA Verified | — | 75.6% |
| Vectara Hallucination Rate | — | 8.7% |
| LMArena Expert | — | 1486 |
Multimodal Not comparable
GPT-5.2 Codex: —, GPT-6 Astra: 55.1 (#3)
| Benchmark | GPT-5.2 Codex | GPT-6 Astra |
|---|---|---|
| LMArena Vision | — | 1280 |
| Blueprint-Bench 2 | — | 49.7% |
| Furniture Assembly | — | 80% |
| LMArena Document | — | 1468 |
Multilingual Not comparable
GPT-5.2 Codex: —, GPT-6 Astra: 54.0 (#53)
| Benchmark | GPT-5.2 Codex | GPT-6 Astra |
|---|---|---|
| LMArena Non-English | — | 1431 |
| LMArena Chinese | — | 1495 |
| LMArena French | — | 1467 |
| LMArena Russian | — | 1434 |
| LMArena Spanish | — | 1412 |
Instruction Following Not comparable
GPT-5.2 Codex: —, GPT-6 Astra: 76.6 (#37)
| Benchmark | GPT-5.2 Codex | GPT-6 Astra |
|---|---|---|
| LMArena Instruction Following | — | 1454 |
Long Context Not comparable
GPT-5.2 Codex: —, GPT-6 Astra: 44.7 (#57)
| Benchmark | GPT-5.2 Codex | GPT-6 Astra |
|---|---|---|
| LMArena Longer Query | — | 1460 |
Writing & Preference Not comparable
GPT-5.2 Codex: —, GPT-6 Astra: 75.7 (#7)
| Benchmark | GPT-5.2 Codex | GPT-6 Astra |
|---|---|---|
| LMArena Text | — | 1443 |
| LMArena Creative Writing | — | 1423 |
| EQ-Bench Creative Writing | — | 2173 |
| LMArena Multi-Turn | — | 1457 |
Frequently asked questions
Is GPT-5.2 Codex better than GPT-6 Astra?
GPT-6 Astra is the stronger model overall, scoring 70.3 to 42.2 on the Noometry Index. GPT-5.2 Codex costs 4.2× less per token, which makes it the better buy when GPT-6 Astra's lead doesn't matter for your workload.
Which is cheaper, GPT-5.2 Codex or GPT-6 Astra?
GPT-5.2 Codex is cheaper. It lists at $1.75 per million input tokens and $14 per million output tokens; GPT-6 Astra lists at $10 and $50.
Is GPT-5.2 Codex or GPT-6 Astra better for coding?
GPT-6 Astra scores higher on coding benchmarks: 70.5 versus 45.4 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Astra does, with 1.05M tokens against 400K.
How many benchmarks do GPT-5.2 Codex and GPT-6 Astra share?
2 benchmarks have published results for both models. GPT-5.2 Codex has 5 scored results on Noometry and GPT-6 Astra has 51.