Model comparison
GPT-4 Turbo vs Muse Spark 1.3
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 30.5 on the Noometry Index.
Last verified . 24 shared benchmarks.
MetaSummary
- They share 24 benchmarks with published results for both. GPT-4 Turbo scores higher in 0 categories and Muse Spark 1.3 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Muse Spark 1.3 leads 73.1 to 9.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.7% for GPT-4 Turbo and 99.2% for Muse Spark 1.3.
- Muse Spark 1.3 is cheaper at $1.25 / $4.25 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
- Muse Spark 1.3 accepts more context: 1.05M tokens versus 128K.
Side by side
| GPT-4 Turbo | Muse Spark 1.3 | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 30.5 | 54.8 |
| Released | 2023-11-06 | 2026-09-02 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 1.05M |
| Max output | 4K | 131K |
| Input $ / M tokens | $10 | $1.25 |
| Output $ / M tokens | $30 | $4.25 |
| Results tracked | 36 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.3 leads
GPT-4 Turbo: 33.8 (#249), Muse Spark 1.3: 56.6 (#21)
| Benchmark | GPT-4 Turbo | Muse Spark 1.3 |
|---|---|---|
| LMArena Coding | 1268 | 1514 |
| CursorBench | — | 41.6% |
| LMArena WebDev | — | 1657 |
| SciCode | — | 59.7% |
| WeirdML | 18% | — |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 58.2% | — |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Not comparable
GPT-4 Turbo: —, Muse Spark 1.3: 38.6 (#30)
| Benchmark | GPT-4 Turbo | Muse Spark 1.3 |
|---|---|---|
| APEX-Agents | — | 57.8% |
| GDP.pdf | — | 27.6% |
| METR Time Horizons | 36.7% | — |
Reasoning Muse Spark 1.3 leads
GPT-4 Turbo: 15.3 (#317), Muse Spark 1.3: 54.0 (#27)
| Benchmark | GPT-4 Turbo | Muse Spark 1.3 |
|---|---|---|
| Chess Puzzles | 6% | 38% |
| LMArena Hard Prompts | 1251 | 1503 |
| DTBench | 61.6% | 96.5% |
| LMCA | 9.8% | 53.9% |
| Epoch Capabilities Index | 127.25 | 156.75 |
| SimpleBench | 25.1% | — |
| NYT Connections (extended) | — | 85.1% |
| CritPt | — | 26% |
| Mystery Game Puzzles | — | 25% |
| Bench to the Future 3 | — | 0.14 |
| ForecastBench | 59.4 | — |
Math Muse Spark 1.3 leads
GPT-4 Turbo: 9.0 (#322), Muse Spark 1.3: 73.1 (#21)
| Benchmark | GPT-4 Turbo | Muse Spark 1.3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 0.7% | 74.4% |
| OTIS Mock AIME 2024-2025 | 6.7% | 99.2% |
| LMArena Math | 1272 | 1494 |
| FrontierMath Tier 4 | — | 46.3% |
| ProofBench | — | 58% |
| MATH Level 5 | 46.7% | — |
Knowledge Muse Spark 1.3 leads
GPT-4 Turbo: 24.3 (#268), Muse Spark 1.3: 42.6 (#95)
| Benchmark | GPT-4 Turbo | Muse Spark 1.3 |
|---|---|---|
| LMArena Expert | 1223 | 1516 |
| GPQA Diamond | 46.6% | — |
| Confabulations | 28.4% | — |
| MMLU | 81.3% | — |
Multimodal Muse Spark 1.3 leads
GPT-4 Turbo: 30.6 (#110), Muse Spark 1.3: 43.7 (#22)
| Benchmark | GPT-4 Turbo | Muse Spark 1.3 |
|---|---|---|
| LMArena Vision | 1090 | 1309 |
| LMArena Document | — | 1471 |
Multilingual Muse Spark 1.3 leads
GPT-4 Turbo: 40.5 (#216), Muse Spark 1.3: 57.4 (#8)
| Benchmark | GPT-4 Turbo | Muse Spark 1.3 |
|---|---|---|
| LMArena Non-English | 1245 | 1481 |
| LMArena Chinese | 1242 | 1529 |
| LMArena French | 1276 | 1524 |
| LMArena German | 1259 | 1515 |
| LMArena Japanese | 1194 | 1474 |
| LMArena Korean | 1187 | 1501 |
| LMArena Russian | 1259 | 1490 |
| LMArena Spanish | 1260 | 1490 |
Instruction Following Muse Spark 1.3 leads
GPT-4 Turbo: 65.8 (#216), Muse Spark 1.3: 77.5 (#22)
| Benchmark | GPT-4 Turbo | Muse Spark 1.3 |
|---|---|---|
| LMArena Instruction Following | 1249 | 1477 |
Long Context Muse Spark 1.3 leads
GPT-4 Turbo: 38.0 (#206), Muse Spark 1.3: 45.6 (#32)
| Benchmark | GPT-4 Turbo | Muse Spark 1.3 |
|---|---|---|
| LMArena Longer Query | 1254 | 1488 |
Writing & Preference Muse Spark 1.3 leads
GPT-4 Turbo: 47.7 (#206), Muse Spark 1.3: 73.6 (#9)
| Benchmark | GPT-4 Turbo | Muse Spark 1.3 |
|---|---|---|
| LMArena Text | 1272 | 1490 |
| LMArena Creative Writing | 1269 | 1455 |
| LMArena Multi-Turn | 1267 | 1482 |
| EQ-Bench Creative Writing | — | 1906 |
Frequently asked questions
Is GPT-4 Turbo better than Muse Spark 1.3?
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 30.5 on the Noometry Index.
Which is cheaper, GPT-4 Turbo or Muse Spark 1.3?
Muse Spark 1.3 is cheaper. It lists at $1.25 per million input tokens and $4.25 per million output tokens; GPT-4 Turbo lists at $10 and $30.
Is GPT-4 Turbo or Muse Spark 1.3 better for coding?
Muse Spark 1.3 scores higher on coding benchmarks: 56.6 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.3 does, with 1.05M tokens against 128K.
How many benchmarks do GPT-4 Turbo and Muse Spark 1.3 share?
24 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Muse Spark 1.3 has 37.