Note: Overall leaderboard rankings may not reflect true model quality — individual benchmarks give a clearer picture. ARC-Challenge MMLU GPQA GSM8K Artificial Analysis Intelligence Index v4.1
← Back to leaderboard

Meta: Muse Spark

28 benchmarks
CompanyMeta
Country of originUSA

Leaderboard position

#69
Overall rank (of 1126 models)
2500
Elo rating
28
Benchmarks
Top 6.1%
Percentile
In Meta (of 12 models)

Benchmark highlights

Nearest competitor from another company

The model from another company with the most similar benchmark scores.

appeared as nearest in 2 of 28 benchmarks

Benchmarks

Predicted scores

Estimated from 25 similar models and the global Elo rating. These are projections, not measured results.

Benchmark Predicted Confidence Based on
MMLU-Pro ~89.12 74% DeepSeek: DeepSeek V4 Pro, Z.ai: GLM 5, Anthropic: claude-opus-4.5
SWE-bench Verified ~84.53 73% DeepSeek: DeepSeek V4 Pro, Nex AGI: Nex-N2 Pro, Z.ai: GLM 5
Terminal-Bench v2.0 ~64.25 73% DeepSeek: DeepSeek V4 Pro, Z.ai: GLM 5, Anthropic: claude-opus-4.5
Claw-Eval ~68.14 72% DeepSeek: DeepSeek V4 Pro, Tencent: hy3, Anthropic: claude-opus-4.5
Artificial Analysis Intelligence Index v4.1.1 (Maximum Reasoning) ~44.47 72% Tencent: hy3, Qwen: Qwen3.7 Max, NVIDIA Corporation: nvidia-nemotron-3-ultra
GPQA ~90.29 71% DeepSeek: DeepSeek V4 Pro, Google: Gemini 3.1 Pro Preview, DeepSeek: DeepSeek V4 Flash
AA-Briefcase ~923.5 71% DeepSeek: DeepSeek V4 Pro, Qwen: Qwen3.7 Max, Z.ai: GLM 5.1
Code Arena - WebDev (Snapshot from july 17, 2026) ~1514.42 70% DeepSeek: DeepSeek V4 Pro, Qwen: qwen3.6-max, Qwen: Qwen3.7 Max
BrowseComp ~80.85 69% DeepSeek: DeepSeek V4 Pro, Tencent: hy3, Nex AGI: Nex-N2 Pro
HMMT Feb 2026 ~92.03 68% Z.ai: GLM 5, Anthropic: claude-opus-4.5, Z.ai: GLM 5.1
LiveCodeBench v6 ~81.77 68% Anthropic: claude-opus-4.5, Qwen: qwen3.6-27b, diffuspace: clover-35b-a3b-preview
WildClawBench ~45 68% DeepSeek: DeepSeek V4 Pro, Nex AGI: Nex-N2 Pro, Z.ai: GLM 5
Artificial Analysis Intelligence Index v4.3.2 ~34.5 67% Qwen: qwen3.6-max, Qwen: Qwen3.7 Max, NVIDIA Corporation: nvidia-nemotron-3-ultra
AIME 2026 ~99.2 66% Z.ai: GLM 5, Anthropic: claude-opus-4.5, Z.ai: GLM 5.1
Artificial Analysis Coding Index (Maximum Reasoning) ~48.19 66% OpenAI: gpt-5.2, OpenAI: gpt-5.3-codex, OpenAI: gpt-5.2-codex
MMLU-Redux ~95.6 65% Qwen: Qwen3.7 Max, Anthropic: claude-opus-4.5, Qwen: qwen3.6-27b
Agent Arena - Net Improvement (Snapshot from july 12, 2026 ~0.18 64% DeepSeek: DeepSeek V4 Pro, Qwen: Qwen3.7 Max, MiniMax: minimax-m2.7
AA-Omniscience Index ~14.32 63% Qwen: Qwen3.7 Max, Google: Gemini 3.1 Pro Preview, NVIDIA Corporation: nvidia-nemotron-3-ultra
CowQA-Rapid ~86.9 63% Qwen: Qwen3.7 Max, Z.ai: GLM 5.1, DeepSeek: DeepSeek V4 Flash
IFEval ~96.75 62% Nex AGI: Nex-N2 Pro, Nex AGI: Nex-N2 Mini, Qwen: Qwen3.5 27B
SuperGPQA ~73.75 62% OpenAI: gpt-5.2, Anthropic: claude-opus-4.5, Qwen: qwen3.6-27b
Search Arena - Arena.ai (Snapshot from july 17, 2026) ~1214.6 62% OpenAI: gpt-5.2, Google: Gemini 3.1 Pro Preview, OpenAI: GPT-5.4
GDPval-AA ~420.13 62% DeepSeek: DeepSeek V4 Pro, Google: Gemini 3.1 Pro Preview, NVIDIA Corporation: nvidia-nemotron-3-ultra
AIME 2025 ~100 61% Z.ai: GLM 5, orcarouter: orcacyber-nano-1.0, Mistral AI: mistral-medium-3.5-128b
CowQA ~97.22 61% Z.ai: GLM 5.1, DeepSeek: DeepSeek V4 Flash, Xiaomi: MiMo-V2.5