Model comparison
GPT-4o mini vs Muse Spark
Muse Spark is the stronger model overall, scoring 50.3 to 25.4 on the Noometry Index.
Last verified . 20 shared benchmarks.
MetaSummary
- They share 20 benchmarks with published results for both. GPT-4o mini scores higher in 0 categories and Muse Spark in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 17.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.9% for GPT-4o mini and 88.9% for Muse Spark.
Side by side
| GPT-4o mini | Muse Spark | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 25.4 | 50.3 |
| Released | 2024-07-18 | 2026-04-08 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 60 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark leads
GPT-4o mini: 21.6 (#330), Muse Spark: 45.6 (#65)
| Benchmark | GPT-4o mini | Muse Spark |
|---|---|---|
| LMArena Coding | 1290 | 1482 |
| Aider Polyglot | 3.6% | — |
| SciCode | — | 51.5% |
| WeirdML | 11.8% | — |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 43.1% | — |
| BigCodeBench Complete | 57.4% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 72.2% | — |
Agentic & Tool Use Not comparable
GPT-4o mini: 27.2 (#95), Muse Spark: —
| Benchmark | GPT-4o mini | Muse Spark |
|---|---|---|
| BALROG | 17.4% | — |
Reasoning Muse Spark leads
GPT-4o mini: 8.7 (#343), Muse Spark: 34.9 (#61)
| Benchmark | GPT-4o mini | Muse Spark |
|---|---|---|
| LMArena Hard Prompts | 1267 | 1475 |
| Epoch Capabilities Index | 126.56 | 152.09 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 10.7% | — |
| Kagi LLM Benchmark | 28.8% | — |
| CritPt | — | 11.3% |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 32.8% | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 54.4% | — |
| LiveBench Data Analysis | 50% | — |
| LMCA | 10.4% | — |
| LiveBench | 41.3% | — |
| PIQA | 88.7% | — |
Math Muse Spark leads
GPT-4o mini: 9.9 (#307), Muse Spark: 46.8 (#57)
| Benchmark | GPT-4o mini | Muse Spark |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.9% | 88.9% |
| LMArena Math | 1267 | 1455 |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| ProofBench | — | 17% |
| Omni-MATH | 28% | — |
| LiveBench Math | 36.3% | — |
| MATH Level 5 | 52.6% | — |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
| GSM8K | 91.3% | — |
Knowledge Muse Spark leads
GPT-4o mini: 17.7 (#279), Muse Spark: 65.7 (#12)
| Benchmark | GPT-4o mini | Muse Spark |
|---|---|---|
| GPQA Diamond | 37.7% | 89.8% |
| LMArena Expert | 1235 | 1458 |
| Humanity's Last Exam | — | 40.6% |
| SimpleQA Verified | 8.3% | — |
| MMLU-Pro | 60.3% | — |
| Confabulations | 37.2% | — |
| GPQA (HELM) | 36.8% | — |
| BoolQ | 88.7% | — |
| MMLU | 81.8% | — |
Multimodal Muse Spark leads
GPT-4o mini: 25.3 (#117), Muse Spark: 42.7 (#23)
| Benchmark | GPT-4o mini | Muse Spark |
|---|---|---|
| LMArena Vision | 1066 | 1306 |
| Video-MME | 64.8% | — |
| GeoBench | 64% | — |
| VPCT | 34% | — |
| LMArena Document | — | 1444 |
Multilingual Muse Spark leads
GPT-4o mini: 42.2 (#194), Muse Spark: 56.3 (#23)
| Benchmark | GPT-4o mini | Muse Spark |
|---|---|---|
| LMArena Non-English | 1266 | 1464 |
| LMArena Chinese | 1264 | 1507 |
| LMArena French | 1296 | 1497 |
| LMArena German | 1272 | 1497 |
| LMArena Korean | 1195 | 1457 |
| LMArena Russian | 1275 | 1467 |
| LMArena Spanish | 1276 | 1471 |
| LMArena Japanese | 1216 | — |
Instruction Following Muse Spark leads
GPT-4o mini: 62.1 (#234), Muse Spark: 76.1 (#47)
| Benchmark | GPT-4o mini | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1259 | 1443 |
| LiveBench Instruction Following | 56.8% | — |
| IFEval | 78.2% | — |
Long Context Muse Spark leads
GPT-4o mini: 39.1 (#181), Muse Spark: 44.4 (#65)
| Benchmark | GPT-4o mini | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1289 | 1451 |
Writing & Preference Muse Spark leads
GPT-4o mini: 39.7 (#243), Muse Spark: 66.2 (#37)
| Benchmark | GPT-4o mini | Muse Spark |
|---|---|---|
| LMArena Text | 1286 | 1474 |
| LMArena Creative Writing | 1268 | 1460 |
| LMArena Multi-Turn | 1285 | 1477 |
| Short-Story Creative Writing | 67.2% | — |
| EQ-Bench Creative Writing | 873 | — |
| WildBench | 79.1% | — |
| LiveBench Language | 28.6% | — |
Frequently asked questions
Is GPT-4o mini better than Muse Spark?
Muse Spark is the stronger model overall, scoring 50.3 to 25.4 on the Noometry Index.
Is GPT-4o mini or Muse Spark better for coding?
Muse Spark scores higher on coding benchmarks: 45.6 versus 21.6 in the Noometry coding category.
How many benchmarks do GPT-4o mini and Muse Spark share?
20 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and Muse Spark has 27.