Up to four models
GPT-5.6 Terra vs Muse Spark 1.3
On the index (GPT-4 = 100), GPT-5.6 Terra scores 172 and Muse Spark 1.3 169. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
GPT-5.6 Terra
172156–188
WeightsClosed
ReleasedJul 2026
Price in / out$2.0 / $12
Context1.05M
Core tests taken6 of 9
169153–186
WeightsClosed
ReleasedSep 2026
Price in / out$1.25 / $4.25
Context1.05M
Core tests taken4 of 9
GPT-5.6 Terra and Muse Spark 1.3 are too close to call (2 points apart, within the uncertainty), ahead on 2 of 4 shared core tests, at 2.3× the price.
Test by testthird-party results
GPT-5.6 Terra
Muse Spark 1.3
Every result as a table
| Test | GPT-5.6 Terra | Muse Spark 1.3 |
|---|---|---|
| Reasoning & knowledge | ||
| LiveBench Data Analysis | 79.3% | 79.6% |
| LiveBench IF | 64.6% | 78.0% |
| LiveBench Language | 82.9% | 82.8% |
| LiveBench Reasoning | 90.6% | 89.6% |
| SimpleBench | 48.9% | 81.8% |
| Maths | ||
| FrontierMath (tiers 1-3) | 86.0% | 74.4% |
| AIME-style maths (OTIS mock) | 99.7% | 99.2% |
| LiveBench Mathematics | 94.9% | 96.0% |
| ProofBench v1.1 | 74.0% | 55.0% |
| Chess puzzles | 47.0% | 37.0% |
| FrontierMath (tier 4) | 70.7% | 46.3% |
| Coding | ||
| Terminal-Bench 4.0 | 22.7% | 10.6% |
| LiveBench Agentic Coding | 54.9% | 64.1% |
| LiveBench Coding | 78.3% | 81.1% |
| Code Migration | 47.8% | 27.6% |
| CyberBench v1.1 | 72.1% | 69.4% |
| IOI | 87.6% | 43.9% |
| ProgramBench | 0.5% | 0.5% |
| Vibe Code Bench v1.1 | 74.6% | 82.9% |
| MirrorCode | 41.1% | 54.4% |
| Agents | ||
| APEX-Agents | 58.2% | 58.6% |
| Terminal-Bench-Science | 10.0% | 4.3% |
| DTBench | 93.3% | 96.5% |
| LMCA | 54.9% | 53.9% |
| Mystery game puzzles | 35.0% | 25.0% |
| Professional work | ||
| Finance Agent (v2) | 54.4% | 58.9% |
| EMB | 66.2% | 62.7% |
| Legal Research Bench | 41.3% | 40.9% |
| Tax Agent Bench | 30.0% | 37.9% |
Tests at least two of these models have taken. Bold rows are the core tests.