Model comparison
GPT-5.6 Terra vs Muse Spark
GPT-5.6 Terra is the stronger model overall, scoring 59.1 to 50.3 on the Noometry Index.
Last verified . 24 shared benchmarks.
MetaSummary
- They share 24 benchmarks with published results for both. GPT-5.6 Terra scores higher in 7 categories and Muse Spark in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Terra leads 81.5 to 46.8.
- The biggest single-benchmark swing is ProofBench: 74% for GPT-5.6 Terra and 17% for Muse Spark.
Side by side
| GPT-5.6 Terra | Muse Spark | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 59.1 | 50.3 |
| Released | 2026-07-09 | 2026-04-08 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | — |
| Max output | 128K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $12 | — |
| Results tracked | 52 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.6 Terra leads
GPT-5.6 Terra: 57.1 (#16), Muse Spark: 45.6 (#65)
| Benchmark | GPT-5.6 Terra | Muse Spark |
|---|---|---|
| SciCode | 55% | 51.5% |
| LMArena Coding | 1484 | 1482 |
| DeepSWE | 69.6% | — |
| FrontierCode | 41.3% | — |
| CursorBench | 41.3% | — |
| LMArena WebDev | 1520 | — |
| WeirdML | 78.3% | — |
| ALE-Bench | 1,951 | — |
Agentic & Tool Use Not comparable
GPT-5.6 Terra: 40.2 (#23), Muse Spark: —
| Benchmark | GPT-5.6 Terra | Muse Spark |
|---|---|---|
| APEX-Agents | 58.2% | — |
| BALROG | 53.2% | — |
| GDP.pdf | 24.7% | — |
| Vending-Bench 2 | 7,343 | — |
Reasoning GPT-5.6 Terra leads
GPT-5.6 Terra: 60.6 (#19), Muse Spark: 34.9 (#61)
| Benchmark | GPT-5.6 Terra | Muse Spark |
|---|---|---|
| CritPt | 30% | 11.3% |
| LMArena Hard Prompts | 1467 | 1475 |
| Epoch Capabilities Index | 159.31 | 152.09 |
| ARC-AGI-2 | 83.9% | — |
| SimpleBench | 48.9% | — |
| Kagi LLM Benchmark | 51.3% | — |
| NYT Connections (extended) | 78.4% | — |
| ARC-AGI-1 | 96.5% | — |
| Chess Puzzles | 54% | — |
| Mystery Game Puzzles | 35% | — |
| DTBench | 93.3% | — |
| LMCA | 55% | — |
| Surface Evolver Bench | 83.8% | — |
Math GPT-5.6 Terra leads
GPT-5.6 Terra: 81.5 (#10), Muse Spark: 46.8 (#57)
| Benchmark | GPT-5.6 Terra | Muse Spark |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 99.7% | 88.9% |
| ProofBench | 74% | 17% |
| LMArena Math | 1463 | 1455 |
| FrontierMath (Tiers 1-3) | 86% | — |
| FrontierMath Tier 4 | 70.7% | — |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Muse Spark leads
GPT-5.6 Terra: 61.3 (#27), Muse Spark: 65.7 (#12)
| Benchmark | GPT-5.6 Terra | Muse Spark |
|---|---|---|
| GPQA Diamond | 93.3% | 89.8% |
| LMArena Expert | 1492 | 1458 |
| Humanity's Last Exam | — | 40.6% |
| SimpleQA Verified | 43.2% | — |
Multimodal GPT-5.6 Terra leads
GPT-5.6 Terra: 47.5 (#10), Muse Spark: 42.7 (#23)
| Benchmark | GPT-5.6 Terra | Muse Spark |
|---|---|---|
| LMArena Vision | 1271 | 1306 |
| LMArena Document | 1472 | 1444 |
| Blueprint-Bench 2 | 30.8% | — |
| Furniture Assembly | 54.2% | — |
Multilingual Muse Spark leads
GPT-5.6 Terra: 54.5 (#42), Muse Spark: 56.3 (#23)
| Benchmark | GPT-5.6 Terra | Muse Spark |
|---|---|---|
| LMArena Non-English | 1439 | 1464 |
| LMArena Chinese | 1514 | 1507 |
| LMArena French | 1476 | 1497 |
| LMArena German | 1462 | 1497 |
| LMArena Korean | 1420 | 1457 |
| LMArena Russian | 1450 | 1467 |
| LMArena Spanish | 1455 | 1471 |
| LMArena Japanese | 1446 | — |
Instruction Following Too close to call
GPT-5.6 Terra: 76.6 (#38), Muse Spark: 76.1 (#47)
| Benchmark | GPT-5.6 Terra | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1453 | 1443 |
Long Context Too close to call
GPT-5.6 Terra: 44.4 (#64), Muse Spark: 44.4 (#65)
| Benchmark | GPT-5.6 Terra | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1452 | 1451 |
Writing & Preference GPT-5.6 Terra leads
GPT-5.6 Terra: 70.4 (#21), Muse Spark: 66.2 (#37)
| Benchmark | GPT-5.6 Terra | Muse Spark |
|---|---|---|
| LMArena Text | 1446 | 1474 |
| LMArena Creative Writing | 1411 | 1460 |
| LMArena Multi-Turn | 1451 | 1477 |
| EQ-Bench Creative Writing | 1855 | — |
| EQ-Bench 4 | 1234 | — |
Frequently asked questions
Is GPT-5.6 Terra better than Muse Spark?
GPT-5.6 Terra is the stronger model overall, scoring 59.1 to 50.3 on the Noometry Index.
Is GPT-5.6 Terra or Muse Spark better for coding?
GPT-5.6 Terra scores higher on coding benchmarks: 57.1 versus 45.6 in the Noometry coding category.
How many benchmarks do GPT-5.6 Terra and Muse Spark share?
24 benchmarks have published results for both models. GPT-5.6 Terra has 52 scored results on Noometry and Muse Spark has 27.