Skip to main content

Benchmark profile

LiveBench

A frequently refreshed benchmark with objective scoring across reasoning, coding, agentic coding, mathematics, data analysis, language, and instruction following.

Data verified

How we show LiveBench

We mirror the official LiveBench 2026-06-25 release: 40 model variants across 23 objective tasks in 7 categories. The visible score is the mean of the seven category averages, matching the source leaderboard.

LiveBench refreshes its questions to limit contamination, but each row still carries a specific model version and reasoning-effort setting. We keep the mirror display only and preserve the category and cost fields in the snapshot instead of collapsing them into weighted model scores.

40 model variants23 tasks7 categoriesRelease 2026-06-25Display only

LiveBench overall score on LiveBench — June 25, 2026

BenchLM mirrors the published livebench overall score view for LiveBench. GPT-5.6 Sol (max effort) leads the public snapshot at 82.4% , followed by Claude Fable 5 (max effort) (80.8%) and GPT-5.5 (xhigh effort) (79.9%). BenchLM does not use these results to rank models overall.

40 modelsExternal benchmark mirrorsRefreshingDisplay onlyUpdated June 25, 2026

LiveBench overall score table (40 models)

Score
1
GPT-5.6 Sol (max effort)OpenAI · Closed
82.4%
2
Claude Fable 5 (max effort)Anthropic · Closed
80.8%
3
GPT-5.5 (xhigh effort)OpenAI · Closed
79.9%
4
79.8%
5
79.7%
6
79.5%
7
78.9%
8
GPT-5.5 (high effort)OpenAI · Closed
78.7%
9
Kimi K3Moonshot AI · Closed
78.5%
10
GPT-5.4 (xhigh effort)OpenAI · Closed
78.0%
11
77.1%
12
76.5%
13
Grok 4.5xAI · Closed
76.2%
14
76.2%
15
75.1%
16
74.8%
17
74.6%
18
GPT-5.2 (high effort)OpenAI · Closed
74.6%
19
74.5%
20
74.3%
21
74.3%
22
GPT-5.2-CodexOpenAI · Closed
74.0%
23
GLM-5.2Z.AI · Open weight
73.2%
24
Qwen3.7 Max (max effort)Alibaba · Closed
73.1%
25
73.0%
26
72.6%
27
GPT-5.5OpenAI · Closed
72.2%
28
Inkling (xhigh effort)Thinking Machines Lab · Open weight
71.7%
29
DeepSeek V4 ProDeepSeek · Open weight
71.6%
30
71.0%
31
Kimi K2.6Moonshot AI · Open weight
70.5%
32
69.6%
33
Qwen3.6 PlusAlibaba · Closed
68.9%
34
Kimi K2.7 CodeMoonshot AI · Open weight
68.4%
35
Grok Build 0.1xAI · Closed
67.8%
36
MiniMax M3MiniMax · Open weight
67.3%
37
66.4%
38
DeepSeek V4 FlashDeepSeek · Open weight
65.5%
39
Qwen3.6-27BAlibaba · Open weight
64.0%
40
Grok 4.3xAI · Closed
62.2%

The published LiveBench snapshot is tightly clustered at the top: GPT-5.6 Sol (max effort) sits at 82.4%, while the third row is only 2.5 points behind. The broader top-10 spread is 4.4 points, so many of the published scores sit in a relatively narrow band.

40 models have been evaluated on LiveBench. The benchmark falls in the External benchmark mirrors category. BenchLM tracks this category separately from its weighted global scoring system, so these results are best compared on the dedicated Korean benchmark views. LiveBench is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About LiveBench

Year

2024

Tasks

23 objective tasks across 7 categories

Format

Mean of category averages

Difficulty

Broad frontier-model evaluation

LiveBench rotates questions to limit contamination and scores answers against objective ground truth. We mirror the current release-specific table, including category scores and cost fields. The overall score is the mean of category averages. Model versions and reasoning-effort settings remain separate, and the mirror does not feed weighted rankings.

BenchLM freshness & provenance

Version

LiveBench 2024

Refresh cadence

Annual

Staleness state

Refreshing

Question availability

Public benchmark set

RefreshingDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

FAQ

What does LiveBench measure?

A frequently refreshed benchmark with objective scoring across reasoning, coding, agentic coding, mathematics, data analysis, language, and instruction following.

Which model leads the published LiveBench snapshot?

GPT-5.6 Sol (max effort) currently leads the published LiveBench snapshot with 82.4% livebench overall score. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on LiveBench?

40 AI models are included in BenchLM's mirrored LiveBench snapshot, based on the public leaderboard captured on June 25, 2026.

Last updated: June 25, 2026 · mirrored from the public benchmark leaderboard

The AI models change fast. We track them for you.

A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.