VECTOR WIREAI INTELLIGENCE
NVDA$1,847+3.2%MSFT$512+1.1%GOOGL$199-0.4%META$728+2.7%AMD$184-1.2%TSM$212+0.6%PLTR$98+4.1%AI IDX4,821+1.9%
PKT
SEEDRefresh Models Deals Regulatory Sources

Kimi K2.5 vs Qwen3.7 Max

MoonshotvsAlibaba41 shared benchmarks734 head-to-head
BenchmarkKimi K2.5Qwen3.7 Max
AA Agentic Index52.830.9
AA Intelligence3646.7
AA-LCR7374.7
AA-Omniscience-7.313.5
aime_202695.897
arena_elo14501474
arena_text_factuality14451479
Artificial Analysis Coding Index46.866
coding_arena_elo14361517
critpt3.113.4
gdpval38.338.5
GPQA Diamond87.992.4
HLE50.241.4
HLE (with tools)51.853.5
hmmt_feb_202687.197.1
hmmt_nov_202591.195
IFBench70.280.5
imo_answer_bench81.890
livebench69.174.3
LiveCodeBench v68591.6
longbench_v26165.3
MCP Atlas6476.4
mcpmark29.560.8
MMLU-Pro87.189.6
nl2repo3247.2
OmniScience Accuracy35.231.1
OmniScience Non-Hallucination5074.4
PaperBench63.564.8
scicode4953.5
simplebench46.870.4
simpleqa_verified36.958.5
SWE-bench Multilingual7378.3
SWE-bench Pro53.860.6
SWE-bench Verified76.880.4
TauBench V3 - Banking14.211.8
Terminal-Bench 2.050.869.7
Terminal-Bench 2.145.775
Terminal-Bench Hard34.850.8
WideSearch7975.2
τ²-Bench Telecom (AA run)95.994.7
τ³-Bench6610.9

Best tracked score per model per benchmark (default configuration; source-attributed). ↓ marks lower-is-better metrics. Open either model for its full surface, provenance and pricing.