Score history · Gemini 3.8 Flash 8 rows

Not enough history to chart — 8 observations, all dated 25 Jun 2026. Rows under different configurations count separately; the list below shows each one.

81.41%release=2026-06-25 · subtasks=["paraphrase","simplify","story_generation","summarize"] · livebench_model_id=gemini-3.8-flash-high25 Jun 2026
87.79%release=2026-06-25 · subtasks=["connections","plot_unscrambling","typos"] · livebench_model_id=gemini-3.8-flash-high25 Jun 2026
54.01%release=2026-06-25 · subtasks=["consecutive_events","tablejoin","tablereformat"] · livebench_model_id=gemini-3.8-flash-high25 Jun 2026
91.56%release=2026-06-25 · subtasks=["AMPS_Hard","integrals_with_game","math_comp","olympiad"] · livebench_model_id=gemini-3.8-flash-high25 Jun 2026
54.24%release=2026-06-25 · subtasks=["javascript","typescript","python"] · livebench_model_id=gemini-3.8-flash-high25 Jun 2026
72.49%release=2026-06-25 · subtasks=["code_generation","code_completion"] · livebench_model_id=gemini-3.8-flash-high25 Jun 2026
89.29%release=2026-06-25 · subtasks=["theory_of_mind","zebra_puzzle","spatial","logic_with_navigation"] · livebench_model_id=gemini-3.8-flash-high25 Jun 2026
75.83%release=2026-06-25 · aggregation=mean of category averages; category = mean of its subtasks · livebench_model_id=gemini-3.8-flash-high25 Jun 2026

Back to the full leaderboard

Leaderboard 0 current results · config contains “["code_generation","code_completion"]”

Select models with +, then open Compare.

No result matches this configuration filter

Clear the filter

The config filter matches a value inside each result's configuration (server-side, `config=` on the API). Chips are the values shared by several rows on the first page; per-model identifiers are not offered.

Definition

Category: general
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 5 h agomedium
Task: contamination-limited, monthly refreshed questions across 6 categories
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 5 h agomedium
Metric: average score · %
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 5 h agomedium
Paper: https://arxiv.org/abs/2406.19314
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 5 h agomedium
Website: livebench.ai
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 5 h agomedium

Each value shows its source, tier and observation time. Missing rows mean no source stated them. How results are recorded →

Evaluated models: claude-opus-4-5-20251101-thinking-64k-high-effort, Claude 4.6 Opus Thinking High Effort, claude-opus-4-7-xhigh-effort, claude-sonnet-4-6-thinking-auto-medium-effort, Claude Sonnet 5 xHigh Effort, deepseek-v4-flash, deepseek-v4-pro, Gemini 3.1 Pro Preview High +49(57 total)

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history

6 claims · 6 properties

Categorycategory1

Claim history for Category
Value	Valid from → to	Status	Source	Confidence	Extractor
general	11 Sept 2026 20:50 UTC → current	current	AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2	medium	curated

Metricmetric1

Claim history for Metric
Value	Valid from → to	Status	Source	Confidence	Extractor
average score	11 Sept 2026 20:50 UTC → current	current	AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2	medium	curated

Paperpaper1

Claim history for Paper
Value	Valid from → to	Status	Source	Confidence	Extractor
https://arxiv.org/abs/2406.19314	11 Sept 2026 20:50 UTC → current	current	AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2	medium	curated

Tasktask1

Claim history for Task
Value	Valid from → to	Status	Source	Confidence	Extractor
contamination-limited, monthly refreshed questions across 6 categories	11 Sept 2026 20:50 UTC → current	current	AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2	medium	curated

Unitunit1

Claim history for Unit
Value	Valid from → to	Status	Source	Confidence	Extractor
%	11 Sept 2026 20:50 UTC → current	current	AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2	medium	curated

Websitewebsite1

Claim history for Website
Value	Valid from → to	Status	Source	Confidence	Extractor
https://livebench.ai	11 Sept 2026 20:50 UTC → current	current	AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2	medium	curated

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

11 Sept 2026
New benchmarkBenchmarkLiveBench
New benchmark: LiveBench
registry
livebench.ai

Full timeline →

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
LiveBench	livebench.ai/table_2026_06_25.csv	leaderboard	T2· Quality secondary	3 h ago	1

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.