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

AI Models & LLM Intelligence Leaderboard

Comprehensive, zero-drift AI benchmarks aggregated across LMSYS Arena.ai (October 2026 Snapshot), Artificial Analysis (quality/speed ratio & price), SWE-bench Verified, GPQA Diamond, LiveBench, and MTEB.

#1 Frontier Reasoning
Gemini 4 Argon (High)
Google DeepMind • Frontier Multimodal
1532 Arena Elo • 82.4% SWE
#1 Coding Champion
Claude Opus 5.5 (High)
Anthropic • Ultra-MoE
1813 Coding Elo • 81.8% SWE
#1 Quality / Speed Ratio
Gemini 3.8 Flash (High)
Google DeepMind • 2000k Context
162 pts Ratio • 185 tps ($0.26/M)
#1 Open Weights / MIT
GLM 5.3 Max (MIT)
Zhipu AI • 380B (42B active)
1474 Arena Elo • $0.60/M
All (29) 🧠 Reasoning 🤖 Agents 💻 Coding ⚡ Speed & Ratio 🚀 LLMs 🔍 Embeddings
License: All Open Proprietary
# Model & Architecture Arena Elo (Human) SWE / GPQA Speed & Ratio Price ($/1M) Context Actions
1
GLM 5.3 Max (MIT)
Zhipu AI • 380B (42B active) • 48GB • open-source
1474 (24.0k)
68.2% SWE
GPQA: 76.2%
88 tps 81 pts
TTFT: 360ms
$0.60
Blended 3:1
256k
Tokens
2
DeepSeek-V4 Pro (High)
DeepSeek • 750B (40B active) • 64GB • open-source
1451 (57.6k)
Agent: 1480
74.2% SWE
GPQA: 80.8%
78 tps 73 pts
TTFT: 410ms
$0.61
Blended 3:1
256k
Tokens
3
Qwen 3.8 27B Instruct
Alibaba Qwen • 27.4B Dense • 16GB • open-source
1440 (25.1k)
67.5% SWE
GPQA: 75%
135 tps 123 pts
TTFT: 210ms
$0.15
Blended 3:1
128k
Tokens
4
Qwen 3.5 397B-A17B
Alibaba Qwen • 397B (17B active) • 32GB • open-source
1437 (95.1k)
68.9% SWE
GPQA: 76.5%
95 tps 87 pts
TTFT: 310ms
$0.27
Blended 3:1
256k
Tokens
5
Gemma 4 26B-A4B
Google DeepMind • 26B (4B active) • 12GB • open-source
1434 (6.1k)
65.8% SWE
GPQA: 73.9%
155 tps 139 pts
TTFT: 180ms
$0.12
Blended 3:1
128k
Tokens
6
DeepSeek-V4 Flash
DeepSeek • 128B (12B active) • 24GB • open-source
1432 (52.0k)
64.9% SWE
GPQA: 73.1%
180 tps 161 pts
TTFT: 160ms
$0.12
Blended 3:1
256k
Tokens
7
Mistral Large 3
Mistral AI • 140B Dense • 48GB • open-source
1429 (85.8k)
63.8% SWE
GPQA: 72.4%
82 tps 73 pts
TTFT: 380ms
$0.75
Blended 3:1
256k
Tokens
8
DeepSeek-R1 (RL)
DeepSeek • 671B (37B active) • 48GB • open-source
1428 (18.2k)
70.2% SWE
GPQA: 78.4%
62 tps 57 pts
TTFT: 650ms
$0.96
Blended 3:1
128k
Tokens
9
Codestral 2501
Mistral AI • 24B Dense • 16GB • open-weights
1425 (38.0k)
59.4% SWE
GPQA: 67.2%
125 tps 106 pts
TTFT: 260ms
$0.38
Blended 3:1
256k
Tokens
10
Qwen 2.5 Coder 32B
Alibaba Qwen • 32.5B Dense • 20GB • open-source
1230 (5.4k)
61.2% SWE
GPQA: 69.8%
120 tps 104 pts
TTFT: 290ms
$0.18
Blended 3:1
128k
Tokens
11
BAAI BGE-en-ICL
BAAI • 7B Dense • 8GB • open-source
N/A
76.5 MTEB
1.3k docs/s 94 pts
TTFT: 35ms
Free / Local
Blended 3:1
33k
Tokens
12
BAAI BGE-Reranker-v2-m3
BAAI • 567M Cross • 4GB • open-source
N/A
N/A MTEB
850 docs/s 92 pts
TTFT: 45ms
Free / Local
Blended 3:1
8k
Tokens
13
Snowflake Arctic Embed M v2
Snowflake • 305M Dense • 2GB • open-source
N/A
72.4 MTEB
4.8k docs/s 89 pts
TTFT: 15ms
Free / Local
Blended 3:1
8k
Tokens

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