Model comparison
GPT-5.1-Codex vs GPT-6 Sol
GPT-6 Sol is the stronger model overall, scoring 61.8 to 38.6 on the Noometry Index.
Last verified . 3 shared benchmarks.
Summary
- They share 3 benchmarks with published results for both. GPT-5.1-Codex scores higher in 1 category and GPT-6 Sol in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Sol leads 87.2 to 30.3.
- The biggest single-benchmark swing is ProofBench: 9% for GPT-5.1-Codex and 83% for GPT-6 Sol.
- GPT-5.1-Codex is cheaper at $1.25 / $10 per million input/output tokens, against $2 / $10 for GPT-6 Sol.
- GPT-6 Sol accepts more context: 1.05M tokens versus 400K.
Side by side
| GPT-5.1-Codex | GPT-6 Sol | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 38.6 | 61.8 |
| Released | 2025-11-12 | 2026-09-22 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 1.05M |
| Max output | 128K | 128K |
| Input $ / M tokens | $1.25 | $2 |
| Output $ / M tokens | $10 | $10 |
| Results tracked | 6 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
GPT-5.1-Codex: 41.9 (#116), GPT-6 Sol: 60.1 (#11)
| Benchmark | GPT-5.1-Codex | GPT-6 Sol |
|---|---|---|
| LMArena WebDev | 1337 | 1688 |
| ALE-Bench | 1,245 | 2,462 |
| DeepSWE | — | 68.8% |
| FrontierCode | — | 49.3% |
| SWE-bench Verified (bash only) | 66% | — |
| SciCode | — | 57.6% |
| LMArena Coding | — | 1447 |
Agentic & Tool Use Too close to call
GPT-5.1-Codex: 38.0 (#33), GPT-6 Sol: 37.2 (#36)
| Benchmark | GPT-5.1-Codex | GPT-6 Sol |
|---|---|---|
| Terminal-Bench | 60.4% | — |
| APEX-Agents | — | 54.3% |
| GDP.pdf | — | 26.4% |
| METR Time Horizons | 70.8% | — |
| Vending-Bench 2 | — | 14,428 |
Reasoning Not comparable
GPT-5.1-Codex: —, GPT-6 Sol: 74.0 (#9)
| Benchmark | GPT-5.1-Codex | GPT-6 Sol |
|---|---|---|
| ARC-AGI-2 | — | 89.6% |
| NYT Connections (extended) | — | 90.1% |
| ARC-AGI-1 | — | 95.5% |
| CritPt | — | 30.9% |
| EBR-Bench | — | 53.3% |
| LMArena Hard Prompts | — | 1418 |
| Mystery Game Puzzles | — | 56% |
| DTBench | — | 97.3% |
| LMCA | — | 59.1% |
| Epoch Capabilities Index | — | 162.72 |
Math GPT-6 Sol leads
GPT-5.1-Codex: 30.3 (#235), GPT-6 Sol: 87.2 (#7)
| Benchmark | GPT-5.1-Codex | GPT-6 Sol |
|---|---|---|
| ProofBench | 9% | 83% |
| FrontierMath (Tiers 1-3) | — | 89.8% |
| FrontierMath Tier 4 | — | 90% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| LMArena Math | — | 1402 |
Knowledge Not comparable
GPT-5.1-Codex: —, GPT-6 Sol: 64.8 (#15)
| Benchmark | GPT-5.1-Codex | GPT-6 Sol |
|---|---|---|
| GPQA Diamond | — | 94.3% |
| SimpleQA Verified | — | 60.7% |
| Vectara Hallucination Rate | — | 6.5% |
| LMArena Expert | — | 1439 |
Multimodal Not comparable
GPT-5.1-Codex: —, GPT-6 Sol: 47.6 (#10)
| Benchmark | GPT-5.1-Codex | GPT-6 Sol |
|---|---|---|
| LMArena Vision | — | 1245 |
| Blueprint-Bench 2 | — | 36.9% |
| Furniture Assembly | — | 58.3% |
Multilingual Not comparable
GPT-5.1-Codex: —, GPT-6 Sol: 50.5 (#118)
| Benchmark | GPT-5.1-Codex | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | — | 1385 |
| LMArena Chinese | — | 1405 |
| LMArena French | — | 1410 |
| LMArena German | — | 1390 |
| LMArena Japanese | — | 1385 |
| LMArena Korean | — | 1341 |
| LMArena Russian | — | 1401 |
| LMArena Spanish | — | 1384 |
Instruction Following Not comparable
GPT-5.1-Codex: —, GPT-6 Sol: 74.5 (#94)
| Benchmark | GPT-5.1-Codex | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | — | 1412 |
Long Context Not comparable
GPT-5.1-Codex: —, GPT-6 Sol: 43.1 (#108)
| Benchmark | GPT-5.1-Codex | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | — | 1411 |
Writing & Preference Not comparable
GPT-5.1-Codex: —, GPT-6 Sol: 71.9 (#18)
| Benchmark | GPT-5.1-Codex | GPT-6 Sol |
|---|---|---|
| LMArena Text | — | 1395 |
| LMArena Creative Writing | — | 1378 |
| EQ-Bench Creative Writing | — | 2125 |
| LMArena Multi-Turn | — | 1412 |
Frequently asked questions
Is GPT-5.1-Codex better than GPT-6 Sol?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 38.6 on the Noometry Index.
Which is cheaper, GPT-5.1-Codex or GPT-6 Sol?
GPT-5.1-Codex is cheaper. It lists at $1.25 per million input tokens and $10 per million output tokens; GPT-6 Sol lists at $2 and $10.
Is GPT-5.1-Codex or GPT-6 Sol better for coding?
GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 41.9 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Sol does, with 1.05M tokens against 400K.
How many benchmarks do GPT-5.1-Codex and GPT-6 Sol share?
3 benchmarks have published results for both models. GPT-5.1-Codex has 6 scored results on Noometry and GPT-6 Sol has 45.