BenchMark·Hub

LiveBench

S高可信Suite
知识问答通用问答未知

发布方:Abacus.AI

热度28.7▼ 0.1

Overall

livebench / average_score · 28 行结果

排名模型子项分数Metric时间
#1gpt-5.5-xhigh
Overall
livebench
80.5%average_score2026-06-25
#2claude-fable-5-xhigh-effort
Overall
livebench
80.1%average_score2026-06-25
#3claude-opus-4-8-xhigh-effort
Overall
livebench
79.8%average_score2026-06-25
#4gpt-5.5-high
Overall
livebench
79.6%average_score2026-06-25
#5gpt-5.4-xhigh
Overall
livebench
78.8%average_score2026-06-25
#6gemini-3.1-pro-preview-high
Overall
livebench
78.2%average_score2026-06-25
#7claude-opus-4-7-xhigh-effort
Overall
livebench
77%average_score2026-06-25
#8claude-sonnet-5-xhigh-effort
Overall
livebench
75.5%average_score2026-06-25
#9gemini-3.5-flash-high
Overall
livebench
75.4%average_score2026-06-25
#10gpt-5.2-2025-12-11-high
Overall
livebench
75.2%average_score2026-06-25
#11claude-opus-4-6-thinking-auto-high-effort
Overall
livebench
75.1%average_score2026-06-25
#12qwen3.7-max
Overall
livebench
74.1%average_score2026-06-25
#13gpt-5.2-codex
Overall
livebench
74%average_score2026-06-25
#14claude-sonnet-4-6-thinking-auto-medium-effort
Overall
livebench
73.4%average_score2026-06-25
#15glm-5.2
Overall
livebench
73.4%average_score2026-06-25
#16claude-opus-4-5-20251101-thinking-64k-high-effort
Overall
livebench
72.9%average_score2026-06-25
#17deepseek-v4-pro
Overall
livebench
72.6%average_score2026-06-25
#18gpt-5.5
Overall
livebench
72.1%average_score2026-06-25
#19kimi-k2.6-thinking
Overall
livebench
70.9%average_score2026-06-25
#20gpt-5.4-nano-xhigh
Overall
livebench
70.9%average_score2026-06-25
#21qwen3.6-plus
Overall
livebench
69%average_score2026-06-25
#22kimi-k2.7-code
Overall
livebench
68.8%average_score2026-06-25
#23grok-build-0.1
Overall
livebench
68.6%average_score2026-06-25
#24minimax-m3
Overall
livebench
67.5%average_score2026-06-25
#25gpt-5.4-mini-xhigh
Overall
livebench
66.6%average_score2026-06-25
28 条结果 · 当前 1-25
1 / 2