Model comparison
Muse Spark 1.3 vs Tulu 3 (Tülu 3) 70B
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 33.0 on the Noometry Index.
Last verified . 12 shared benchmarks.
Meta
Allen Institute for AI (Ai2)Summary
- They share 12 benchmarks with published results for both. Muse Spark 1.3 scores higher in 8 categories and Tulu 3 (Tülu 3) 70B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Muse Spark 1.3 leads 73.1 to 14.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 99.2% for Muse Spark 1.3 and 4.4% for Tulu 3 (Tülu 3) 70B.
- Tulu 3 (Tülu 3) 70B has downloadable open weights; the other is API-only.
Side by side
| Muse Spark 1.3 | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Meta | Allen Institute for AI (Ai2) |
| Noometry Index | 54.8 | 33.0 |
| Released | 2026-09-02 | 2024-11-21 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 131K | — |
| Input $ / M tokens | $1.25 | — |
| Output $ / M tokens | $4.25 | — |
| Results tracked | 37 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.3 leads
Muse Spark 1.3: 56.6 (#21), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | Muse Spark 1.3 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1514 | 1235 |
| CursorBench | 41.6% | — |
| LMArena WebDev | 1657 | — |
| SciCode | 59.7% | — |
Agentic & Tool Use Not comparable
Muse Spark 1.3: 38.6 (#30), Tulu 3 (Tülu 3) 70B: —
| Benchmark | Muse Spark 1.3 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| APEX-Agents | 57.8% | — |
| GDP.pdf | 27.6% | — |
Reasoning Muse Spark 1.3 leads
Muse Spark 1.3: 54.0 (#27), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | Muse Spark 1.3 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1503 | 1220 |
| NYT Connections (extended) | 85.1% | — |
| CritPt | 26% | — |
| Chess Puzzles | 38% | — |
| Mystery Game Puzzles | 25% | — |
| DTBench | 96.5% | — |
| LMCA | 53.9% | — |
| Bench to the Future 3 | 0.14 | — |
| Epoch Capabilities Index | 156.75 | — |
Math Muse Spark 1.3 leads
Muse Spark 1.3: 73.1 (#21), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | Muse Spark 1.3 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 99.2% | 4.4% |
| LMArena Math | 1494 | 1242 |
| FrontierMath (Tiers 1-3) | 74.4% | — |
| FrontierMath Tier 4 | 46.3% | — |
| ProofBench | 58% | — |
| MATH Level 5 | — | 42.7% |
Knowledge Muse Spark 1.3 leads
Muse Spark 1.3: 42.6 (#95), Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | Muse Spark 1.3 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
| LMArena Expert | 1516 | — |
Multimodal Not comparable
Muse Spark 1.3: 43.7 (#22), Tulu 3 (Tülu 3) 70B: —
| Benchmark | Muse Spark 1.3 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Vision | 1309 | — |
| LMArena Document | 1471 | — |
Multilingual Muse Spark 1.3 leads
Muse Spark 1.3: 57.4 (#8), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | Muse Spark 1.3 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1481 | 1236 |
| LMArena Chinese | 1529 | 1249 |
| LMArena Russian | 1490 | 1246 |
| LMArena French | 1524 | — |
| LMArena German | 1515 | — |
| LMArena Japanese | 1474 | — |
| LMArena Korean | 1501 | — |
| LMArena Spanish | 1490 | — |
Instruction Following Muse Spark 1.3 leads
Muse Spark 1.3: 77.5 (#22), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | Muse Spark 1.3 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1477 | 1233 |
Long Context Muse Spark 1.3 leads
Muse Spark 1.3: 45.6 (#32), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | Muse Spark 1.3 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1488 | 1224 |
Writing & Preference Muse Spark 1.3 leads
Muse Spark 1.3: 73.6 (#9), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | Muse Spark 1.3 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1490 | 1256 |
| LMArena Creative Writing | 1455 | 1231 |
| LMArena Multi-Turn | 1482 | 1252 |
| EQ-Bench Creative Writing | 1906 | — |
Frequently asked questions
Is Muse Spark 1.3 better than Tulu 3 (Tülu 3) 70B?
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 33.0 on the Noometry Index.
Is Muse Spark 1.3 or Tulu 3 (Tülu 3) 70B better for coding?
Muse Spark 1.3 scores higher on coding benchmarks: 56.6 versus 36.0 in the Noometry coding category.
How many benchmarks do Muse Spark 1.3 and Tulu 3 (Tülu 3) 70B share?
12 benchmarks have published results for both models. Muse Spark 1.3 has 37 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.