HLE
30.1 score
AI Leaderboard · Proprietary
Composer 2.5 Fast benchmarks, pricing, and ranking.
Rank #15AskClash overall score: 54.3
$3.00 / $15.0Input and output token price, when published. Context: 200K.
OAuthBilling and access path cached for this model row.
Composer 2.5 Fast benchmark snapshot
AskClash combines public benchmark cells into a weighted percentile score and penalizes missing coverage so narrow rows do not dominate better-measured models.
Overall54.3
Benchmark cells13
Context200K
CreatorCursor
Public benchmark scores
Only benchmark columns with cached public values are shown here. Missing cells remain blank in the live table.
GPQA
87.6 score
MATH-500
82.0 score
IFEval
93.9 score
SWE-bench
76.8 score
SWE-Pro
49.2 score
Terminal-Bench
66.9 score
LiveCodeBench
85.0 score
MCP Atlas
29.5 score
MMMU-Pro
78.5 score
Tau2
95.9 score
Related model comparisons
Use these links to compare nearby frontier and open-weight models from the same AI leaderboard data.
Related AI and tech coverage
Cached AskClash article matches that can provide release, provider, or market context around this model.
Qwen 3.7 🤖, Cursor Composer 2.5 👨💻, Anthropic acquires Stainless 🛠️
Qwen 3.7 🤖, Cursor Composer 2.5 👨💻, Anthropic acquires Stainless 🛠️ TLDR Newsletters Advertise Blog TLDR TLDR AI 2026-05-19 Qwen 3.7 🤖, Cursor Composer 2.5 👨💻, Anthropic acquires Stainless 🛠️ Your architecture blueprint for AI-powered search at scale (Sponsor) Are you asking users to put up with search timeouts, empty results, or irrelevant answers? This Algolia whitepaper lays out the full stack of architecture & data foundations for AI search. Read it to learn how to: Combine lexical precisi
'What if behind the pointer, there was an AI model': Google DeepMind wants to reinvent the humble mouse cursor
PC Gamer
Grok 4.3 🤖, Claude security beta 🛡️, Cursor xAI analysis 📝
Grok 4.3 🤖, Claude security beta 🛡️, Cursor xAI analysis 📝 TLDR Newsletters Advertise TLDR TLDR AI 2026-05-01 Grok 4.3 🤖, Claude security beta 🛡️, Cursor xAI analysis 📝 Don't let your keyboard slow your coding agents down (Sponsor) The best coding agents need context to get it right, but typing takes time. Wispr Flow lets you speak context into Cursor, Claude Code, Codex, and any AI tool. The best part: it's 4x faster than typing. Describe what you want built, explain the edge cases, and give ag
Anthropic Microsoft deal 🤝, Cursor $3B ARR 📈, cloud agent lessons 🤖
Anthropic Microsoft deal 🤝, Cursor $3B ARR 📈, cloud agent lessons 🤖 TLDR Newsletters Advertise Blog TLDR TLDR AI 2026-05-22 Anthropic Microsoft deal 🤝, Cursor $3B ARR 📈, cloud agent lessons 🤖 Defending Against the Next Generation of Agentic AI Attacks. (Sponsor) Can your architecture defend against attacks that are autonomous, adaptive, and faster than anything you've seen before? Frontier AI models are compressing the attack lifecycle and enabling a new generation of agentic threats. Security t
Last cached leaderboard date: May 22, 2026. This model page is generated from the AskClash AI Leaderboard cache and linked from the live leaderboard.