Official AI Models & LLM Benchmark Hub (2026 Live Verified)

AI Models & LLM Intelligence Leaderboard

Comprehensive, zero-drift AI benchmarks aggregated across LMSYS Arena.ai (human Elo), Artificial Analysis (quality/speed ratio & price), SWE-bench Verified, GPQA Diamond, LiveBench, and MTEB.

#1 Frontier Reasoning

Claude Opus 5 (High)

Anthropic • Ultra-MoE

1504 Arena Elo • 78.6% SWE

#1 Test-Time Compute

GPT-5.6 Sol (xHigh)

OpenAI • Adaptive MoE

1498 Arena Elo • 97.6 Intel

#1 Quality / Speed Ratio

Gemini 3.7 Flash

Google • 2M Context

158 pts Ratio • 165 tps ($0.61/M)

#1 Open Weights MIT

DeepSeek-V4 Pro

DeepSeek • 750B MoE

1474 Arena Elo • $0.35/M

All (24) 🧠 Reasoning 🤖 Agents 💻 Coding ⚡ Speed & Ratio 🚀 LLMs 🔍 Embeddings

License: All Open Proprietary

#	Model & Architecture	Arena Elo (Human)	SWE / GPQA	Speed & Ratio	Price ($/1M)	Context	Actions
1	Qwen 3.8 Max Alibaba Qwen • Mega-MoE • proprietary	1482 (10.0k)	70.4% SWE GPQA: 77.8%	115 tps 108 pts TTFT: 260ms	$1.05 Blended 3:1	256k Tokens	Skills
2	GLM 5.3 Max (MIT) Zhipu AI • 380B (42B active) • 48GB • open-source	1477 (3.8k)	68.2% SWE GPQA: 76.2%	88 tps 81 pts TTFT: 360ms	$0.60 Blended 3:1	256k Tokens
3	Qwen 3.5 397B-A17B Alibaba Qwen • 397B (17B active) • 32GB • open-source	1455 (70.2k)	68.9% SWE GPQA: 76.5%	95 tps 87 pts TTFT: 310ms	$0.27 Blended 3:1	256k Tokens	Skills
4	Gemma 4 26B-A4B Google DeepMind • 26B (4B active) • 12GB • open-source	1448 (5.8k)	65.8% SWE GPQA: 73.9%	155 tps 139 pts TTFT: 180ms	$0.12 Blended 3:1	128k Tokens	Skills
5	DeepSeek-V4 Flash DeepSeek • 128B (12B active) • 24GB • open-source	1445 (49.0k)	64.9% SWE GPQA: 73.1%	180 tps 161 pts TTFT: 160ms	$0.12 Blended 3:1	256k Tokens	Skills
6	Mistral Large 3 Mistral AI • 140B Dense • 48GB • open-source	1440 (62.6k)	63.8% SWE GPQA: 72.4%	82 tps 73 pts TTFT: 380ms	$0.75 Blended 3:1	256k Tokens	Skills

Query this Leaderboard via REST API & Agents

Instant, zero-auth JSON endpoint with edge caching for programmatic model selection.

GET https://yakaai.com/api/leaderboard