AI Battle > Rankings > GDPval-AA v2 Leaderboard

GDPval-AA v2 Leaderboard Ranking — eval gdpval (2026)

Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) by Anthropic leads the GDPval-AA v2 Leaderboard ranking with a score of 1764. The ranking covers 20 evaluated eval gdpval from a public dataset that AI Battle re-checks daily.

Last updated: . Source: public benchmark datasets and provider pricing, aggregated daily; 20 entries shown.

Claude Fable 5.1 (Adaptive Reasoning, Max Ef1764Claude Fable 5.1 (Adaptive Reasoning, Xhigh 1745Claude Opus 5 (Adaptive Reasoning, Max Effor1735Claude Opus 5 (Adaptive Reasoning, Xhigh Eff1708Muse Spark 1.3 (max)1703Grok 4.6 (xhigh)1663Muse Spark 1.3 (xhigh)1662GLM-5.3 (max)1655GLM-5.3-Flash1655Claude Fable 5.1 (Adaptive Reasoning, High E1650Grok 4.6 (high)1643DeepSeek V4.1 Flash (Reasoning, Max Effort)1632Claude Fable 5 (Adaptive Reasoning, Max Effo1631Qwen3.8 2.4T A95B1628GPT-5.6 Sol (max)1624GPT-6 Astra (max)1580Kimi K3 (max)1552DeepSeek V4 Pro 0813 (Reasoning, Max Effort)1493GPT-5.6 Luna (max)1489GPT-5.6 Terra (max)1477
Every entry in the dataset, scaled from the smallest to the largest published value.

All 20 entries in this dataset

#EntryCreatorValueΔ vs #1
1Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)Anthropic17640.0%
2Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)Anthropic1745-1.0%
3Claude Opus 5 (Adaptive Reasoning, Max Effort)Anthropic1735-1.6%
4Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)Anthropic1708-3.1%
5Muse Spark 1.3 (max)Meta1703-3.4%
6Grok 4.6 (xhigh)SpaceXAI1663-5.7%
7Muse Spark 1.3 (xhigh)Meta1662-5.7%
8GLM-5.3 (max)Z AI1655-6.2%
9GLM-5.3-FlashZ AI1655-6.2%
10Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)Anthropic1650-6.5%
11Grok 4.6 (high)SpaceXAI1643-6.8%
12DeepSeek V4.1 Flash (Reasoning, Max Effort)DeepSeek1632-7.5%
13Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)Anthropic1631-7.5%
14Qwen3.8 2.4T A95BAlibaba1628-7.7%
15GPT-5.6 Sol (max)OpenAI1624-7.9%
16GPT-6 Astra (max)OpenAI1580-10.4%
17Kimi K3 (max)Kimi1552-12.0%
18DeepSeek V4 Pro 0813 (Reasoning, Max Effort)DeepSeek1493-15.3%
19GPT-5.6 Luna (max)OpenAI1489-15.6%
20GPT-5.6 Terra (max)OpenAI1477-16.3%

How the values are distributed

Across the 20 numeric entries in this window the median is 1646 and the mean is 1635, so the typical entry sits 117 below the leader. The window spans 1477 to 1764.

30208223
8 equal buckets between the smallest (1477) and largest (1764) value; numbers under bars are entry counts.

10 of 20 entries are at or above the median, and the top three hold 16% of the combined value — read it against the metric below, since a higher number is not "better" for every dataset.

Creators in this ranking

8 creators appear in this window; the three most-represented hold 60% of the entries.

CreatorEntriesHighest valueTop entry
Anthropic61764Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)
OpenAI41624GPT-5.6 Sol (max)
Meta21703Muse Spark 1.3 (max)
SpaceXAI21663Grok 4.6 (xhigh)
Z AI21655GLM-5.3 (max)
DeepSeek21632DeepSeek V4.1 Flash (Reasoning, Max Effort)
Alibaba11628Qwen3.8 2.4T A95B
Kimi11552Kimi K3 (max)

Where these models appear in other rankings

The same models are measured across multiple independent datasets. Aggregating the 20 entries above against every other AI Battle dataset gives this cross-section, computed by AI Battle and published nowhere upstream:

ModelDatasetsBest placements elsewhere
Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)35#1/20 in AA-Briefcase Elo, #1/20 in AA-Omniscience Index, #1/20 in Artificial Analysis Intelligence Index by Open Weights / Proprietary
Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)20#2/20 in Humanity's Last Exam: Score, #2/20 in AA-Omniscience Accuracy, #2/20 in AA-Briefcase Rubric Pass Rate by File Type (Normalized)
Claude Opus 5 (Adaptive Reasoning, Max Effort)43#2/20 in AA-Briefcase Elo, #2/20 in AA-Briefcase Elo, #3/20 in Artificial Analysis Intelligence Index by Open Weights / Proprietary
Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)11#4/20 in AA-Briefcase Rubric Pass Rate by File Type (Normalized), #4/20 in AA-Briefcase Elo, #8/20 in Humanity's Last Exam: Score
Muse Spark 1.3 (max)60#3/20 in AA-Briefcase Elo, #3/20 in Output Speed, #3/20 in AA-Briefcase Elo
Grok 4.6 (xhigh)3#15/20 in GDPval-AA v2: Output Tokens per Task, #17/20 in GDPval-AA v2: Average Turns per Task
Muse Spark 1.3 (xhigh)12#3/20 in 𝜏³-Banking: Time per Task, #5/20 in SciCode: Score, #7/20 in GDPval-AA v2: Average Turns per Task
GLM-5.3 (max)56#3/20 in AA-Briefcase Tool Calls Breakdown, Avg per Task, #4/20 in AA-Omniscience Hallucination Rate, #4/20 in Mean Turns per Task
GLM-5.3-Flash53#1/20 in Pricing: Cache Hit, Input, and Output, #1/20 in Pricing: Cache Hit, Input, and Output, #1/20 in AA-Omniscience Index: Cost Breakdown
Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)22#1/20 in SciCode: Output Tokens per Task, #2/20 in AA-Omniscience Index: Token Usage, #2/20 in AA-LCR v1.1: Output Tokens per Task
Grok 4.6 (high)60#2/20 in 𝜏³-Banking: Score, #5/20 in AA-Briefcase Elo, #5/20 in AA-Omniscience Index
DeepSeek V4.1 Flash (Reasoning, Max Effort)55#3/20 in End-to-End Response Time, #3/20 in Latency: Time To First Answer Token, #2/11 in Cost per Task
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)39#2/20 in SciCode: Score, #3/20 in AA-Omniscience Index, #3/20 in AA-Omniscience Index
Qwen3.8 2.4T A95B42#2/14 in Model Size: Total and Active Parameters, #5/20 in AA-Briefcase Tool Calls Breakdown, Avg per Task, #5/20 in 𝜏³-Banking: Score
GPT-5.6 Sol (max)55#3/20 in SciCode: Output Tokens per Task, #4/20 in 𝜏³-Banking: Output Tokens per Task, #5/20 in AA-LCR v1.1: Output Tokens per Task
GPT-6 Astra (max)50#1/19 in MMMU-Pro: Score, #2/20 in AA-Omniscience Index, #2/20 in Artificial Analysis Intelligence Index by Open Weights / Proprietary
Kimi K3 (max)59#1/20 in Context Window, #1/20 in AA-LCR v1.1: Score, #1/14 in Model Size: Total and Active Parameters
DeepSeek V4 Pro 0813 (Reasoning, Max Effort)58#3/14 in Model Size: Total and Active Parameters, #3/12 in Artificial Analysis Openness Index: Score, #3/11 in Cost per Task
GPT-5.6 Luna (max)57#1/11 in Cost per Task, #1/11 in Cost per Task, #3/20 in Pricing: Cache Hit, Input, and Output
GPT-5.6 Terra (max)51#7/20 in AA-Briefcase Output Tokens per Task, #8/20 in Humanity's Last Exam: Output Tokens per Task, #9/20 in Output Speed

Metric reference

This ranking carries the metrics gdpvalAaElo_lower, gdpvalAaElo_mid, gdpvalAaElo_upper from the GDPval-AA v2 Leaderboard dataset in the tab::eval-gdpval family. Units and the direction of "better" are not declared by the source dataset, so AI Battle does not invent them: values are shown exactly as published, and the ordering is the source dataset's own.

How this ranking is built

Rebuilt on from the public dataset GDPval-AA v2 Leaderboard (family tab::eval-gdpval). The source lists 20 entries and all 20 are shown here. AI Battle requests the dataset's rows, keeps the ordering the source publishes, and computes only the statistics on this page: median, mean, spread, the #1–#2 gap, the creator breakdown and the raw-data file. Nothing on this page is generated text about the entries — the numbers come from the source.

Refresh cadence: every deploy re-pulls the dataset, so this page tracks the source's own update cycle. Corrections: see the methodology page.

Limitations

Raw data

Machine-readable copy of this table, with the statistics below and the source provenance: /data/rankings/eval-gdpval-gdpval-aa-v2-leaderboard.json. Free to reuse with attribution to AI Battle and the source dataset.

FAQ — GDPval-AA v2 Leaderboard

What is the best model for GDPval-AA v2 Leaderboard in 2026?

Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) by Anthropic currently leads the GDPval-AA v2 Leaderboard ranking with a score of 1764, the highest value in this dataset across eval gdpval. AI Battle aggregates the dataset from its public source and re-checks it daily.

How often is the GDPval-AA v2 Leaderboard ranking updated?

The GDPval-AA v2 Leaderboard ranking is rebuilt daily from the upstream public dataset. Scores are the source dataset's own published values, so positions track whatever that source last released — each ranking page names the dataset it comes from.

Which models rank in the top 3 for GDPval-AA v2 Leaderboard?

The top 3 are: 1. Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) (1764), 2. Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback) (1745), 3. Claude Opus 5 (Adaptive Reasoning, Max Effort) (1735).

All AI Battle Rankings

Directories