Model comparison
Claude Sonnet 5.5 vs GPT-5.6 Terra
Claude Sonnet 5.5 is the stronger model overall, scoring 61.9 to 59.2 on the Noometry Index.
Last verified . 30 shared benchmarks.
Summary
- They share 30 benchmarks with published results for both. Claude Sonnet 5.5 scores higher in 8 categories and GPT-5.6 Terra in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where Claude Sonnet 5.5 leads 67.3 to 57.7.
- The biggest single-benchmark swing is Mystery Game Puzzles: 65% for Claude Sonnet 5.5 and 35% for GPT-5.6 Terra.
- Claude Sonnet 5.5 is cheaper at $2 / $10 per million input/output tokens, against $2 / $12 for GPT-5.6 Terra.
- GPT-5.6 Terra accepts more context: 1.05M tokens versus 1M.
Side by side
| Claude Sonnet 5.5 | GPT-5.6 Terra | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 61.9 | 59.2 |
| Released | 2026-09-28 | 2026-07-09 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 128K | 128K |
| Input $ / M tokens | $2 | $2 |
| Output $ / M tokens | $10 | $12 |
| Results tracked | 32 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 5.5 leads
Claude Sonnet 5.5: 67.3 (#6), GPT-5.6 Terra: 57.7 (#19)
| Benchmark | Claude Sonnet 5.5 | GPT-5.6 Terra |
|---|---|---|
| FrontierCode | 52.1% | 41.3% |
| CursorBench | 55.5% | 41.3% |
| LMArena WebDev | 1774 | 1522 |
| SciCode | 61% | 55% |
| LMArena Coding | 1513 | 1484 |
| ALE-Bench | 1,819 | 1,951 |
| DeepSWE | — | 69.6% |
| FrontierSWE | 61.9% | — |
| WeirdML | — | 78.3% |
Agentic & Tool Use Claude Sonnet 5.5 leads
Claude Sonnet 5.5: 45.0 (#16), GPT-5.6 Terra: 40.1 (#25)
| Benchmark | Claude Sonnet 5.5 | GPT-5.6 Terra |
|---|---|---|
| APEX-Agents | 75.5% | 58.2% |
| BALROG | — | 53.2% |
| GDP.pdf | — | 24.7% |
| Vending-Bench 2 | — | 7,343 |
Reasoning GPT-5.6 Terra leads
Claude Sonnet 5.5: 54.0 (#28), GPT-5.6 Terra: 60.7 (#21)
| Benchmark | Claude Sonnet 5.5 | GPT-5.6 Terra |
|---|---|---|
| NYT Connections (extended) | 80.5% | 78.4% |
| CritPt | 31.4% | 30% |
| LMArena Hard Prompts | 1495 | 1468 |
| Mystery Game Puzzles | 65% | 35% |
| Epoch Capabilities Index | 165.03 | 159.62 |
| ARC-AGI-2 | — | 83.9% |
| SimpleBench | — | 48.9% |
| Kagi LLM Benchmark | — | 51.3% |
| ARC-AGI-1 | — | 96.5% |
| Chess Puzzles | — | 54% |
| DTBench | — | 93.3% |
| LMCA | — | 55% |
| Surface Evolver Bench | — | 83.8% |
Math Claude Sonnet 5.5 leads
Claude Sonnet 5.5: 87.9 (#6), GPT-5.6 Terra: 81.6 (#12)
| Benchmark | Claude Sonnet 5.5 | GPT-5.6 Terra |
|---|---|---|
| FrontierMath (Tiers 1-3) | 88.8% | 86% |
| FrontierMath Tier 4 | 80.5% | 70.7% |
| OTIS Mock AIME 2024-2025 | 100% | 99.7% |
| ProofBench | 100% | 74% |
| LMArena Math | 1510 | 1466 |
| FrontierMath Erdős | 2.9% | — |
Knowledge Claude Sonnet 5.5 leads
Claude Sonnet 5.5: 66.0 (#12), GPT-5.6 Terra: 61.2 (#30)
| Benchmark | Claude Sonnet 5.5 | GPT-5.6 Terra |
|---|---|---|
| GPQA Diamond | 95.6% | 93.3% |
| SimpleQA Verified | 46.5% | 43.2% |
| LMArena Expert | 1540 | 1492 |
Multimodal Claude Sonnet 5.5 leads
Claude Sonnet 5.5: 51.5 (#6), GPT-5.6 Terra: 47.3 (#11)
| Benchmark | Claude Sonnet 5.5 | GPT-5.6 Terra |
|---|---|---|
| LMArena Vision | 1289 | 1271 |
| Furniture Assembly | 75% | 54.2% |
| Blueprint-Bench 2 | — | 30.8% |
| LMArena Document | — | 1472 |
Multilingual Too close to call
Claude Sonnet 5.5: 55.3 (#30), GPT-5.6 Terra: 54.4 (#44)
| Benchmark | Claude Sonnet 5.5 | GPT-5.6 Terra |
|---|---|---|
| LMArena Non-English | 1452 | 1439 |
| LMArena Chinese | 1522 | 1513 |
| LMArena Russian | 1451 | 1450 |
| LMArena French | — | 1471 |
| LMArena German | — | 1460 |
| LMArena Japanese | — | 1457 |
| LMArena Korean | — | 1425 |
| LMArena Spanish | — | 1448 |
Instruction Following Claude Sonnet 5.5 leads
Claude Sonnet 5.5: 78.3 (#11), GPT-5.6 Terra: 76.4 (#40)
| Benchmark | Claude Sonnet 5.5 | GPT-5.6 Terra |
|---|---|---|
| LMArena Instruction Following | 1495 | 1454 |
Long Context Claude Sonnet 5.5 leads
Claude Sonnet 5.5: 45.9 (#28), GPT-5.6 Terra: 44.4 (#68)
| Benchmark | Claude Sonnet 5.5 | GPT-5.6 Terra |
|---|---|---|
| LMArena Longer Query | 1498 | 1451 |
Writing & Preference GPT-5.6 Terra leads
Claude Sonnet 5.5: 66.0 (#40), GPT-5.6 Terra: 70.2 (#23)
| Benchmark | Claude Sonnet 5.5 | GPT-5.6 Terra |
|---|---|---|
| LMArena Text | 1471 | 1447 |
| LMArena Creative Writing | 1465 | 1410 |
| LMArena Multi-Turn | 1474 | 1449 |
| EQ-Bench Creative Writing | — | 1855 |
| EQ-Bench 4 | — | 1234 |
Frequently asked questions
Is Claude Sonnet 5.5 better than GPT-5.6 Terra?
Claude Sonnet 5.5 is the stronger model overall, scoring 61.9 to 59.2 on the Noometry Index.
Which is cheaper, Claude Sonnet 5.5 or GPT-5.6 Terra?
Claude Sonnet 5.5 is cheaper. It lists at $2 per million input tokens and $10 per million output tokens; GPT-5.6 Terra lists at $2 and $12.
Is Claude Sonnet 5.5 or GPT-5.6 Terra better for coding?
Claude Sonnet 5.5 scores higher on coding benchmarks: 67.3 versus 57.7 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Terra does, with 1.05M tokens against 1M.
How many benchmarks do Claude Sonnet 5.5 and GPT-5.6 Terra share?
30 benchmarks have published results for both models. Claude Sonnet 5.5 has 32 scored results on Noometry and GPT-5.6 Terra has 52.