AI Battle > Rankings > Humanity's Last Exam: Time per Task

Humanity's Last Exam: Time per Task Ranking — Frontier Evals (2026)

Gemini 3.5 Flash-Lite by Google leads the Humanity's Last Exam: Time per Task ranking with a score of 0.48. The ranking covers 20 evaluated frontier evals from a public dataset that AI Battle re-checks daily.

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

Gemini 3.5 Flash-Lite0.48Claude Fable 5.1 (Adaptive Reasoning, Medium0.89Gemini 3.8 Flash (high)1.27GPT-6 Astra (xhigh)1.52Claude Fable 5.1 (Adaptive Reasoning, High E1.60gpt-oss-120b (high)1.68Muse Glimmer (high)2.08DeepSeek V4.1 Flash (Reasoning, Max Effort)2.09GPT-6 Astra (max)2.12Muse Spark 1.3 (max)2.27Nemotron 3 Ultra 550B A55B (Reasoning)2.83Mistral Medium 3.52.86GPT-5.6 Terra (max)2.97Claude Fable 5 (Adaptive Reasoning, Max Effo3.29MiniMax-M33.42GPT-5.6 Luna (max)3.60GPT-5.6 Sol (max)3.62Claude Fable 5.1 (Adaptive Reasoning, Xhigh 3.89Claude Opus 5 (Adaptive Reasoning, Xhigh Eff4.12DeepSeek V4 Pro 0813 (Reasoning, Max Effort)5.10
Every entry in the dataset, scaled from the smallest to the largest published value.

All 20 entries in this dataset

#EntryCreatorValueΔ vs #1
1Gemini 3.5 Flash-LiteGoogle0.480.0%
2Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)Anthropic0.8983.8%
3Gemini 3.8 Flash (high)Google1.27162.5%
4GPT-6 Astra (xhigh)OpenAI1.52213.1%
5Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)Anthropic1.60230.5%
6gpt-oss-120b (high)OpenAI1.68247.9%
7Muse Glimmer (high)Meta2.08330.3%
8DeepSeek V4.1 Flash (Reasoning, Max Effort)DeepSeek2.09331.2%
9GPT-6 Astra (max)OpenAI2.12337.8%
10Muse Spark 1.3 (max)Meta2.27368.5%
11Nemotron 3 Ultra 550B A55B (Reasoning)NVIDIA2.83485.0%
12Mistral Medium 3.5Mistral2.86489.8%
13GPT-5.6 Terra (max)OpenAI2.97512.9%
14Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)Anthropic3.29580.0%
15MiniMax-M3MiniMax3.42606.1%
16GPT-5.6 Luna (max)OpenAI3.60643.1%
17GPT-5.6 Sol (max)OpenAI3.62647.5%
18Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)Anthropic3.89702.7%
19Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)Anthropic4.12751.6%
20DeepSeek V4 Pro 0813 (Reasoning, Max Effort)DeepSeek5.10953.4%

How the values are distributed

Across the 20 numeric entries in this window the median is 2.55 and the mean is 2.59, so the typical entry sits 2.07 above the leader. The window spans 0.48 to 5.10.

23414411
8 equal buckets between the smallest (0.48) and largest (5.10) value; numbers under bars are entry counts.

10 of 20 entries are at or above the median, and the top three hold 25% 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 65% of the entries.

CreatorEntriesHighest valueTop entry
OpenAI63.62GPT-5.6 Sol (max)
Anthropic54.12Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)
DeepSeek25.10DeepSeek V4 Pro 0813 (Reasoning, Max Effort)
Meta22.27Muse Spark 1.3 (max)
Google21.27Gemini 3.8 Flash (high)
MiniMax13.42MiniMax-M3
Mistral12.86Mistral Medium 3.5
NVIDIA12.83Nemotron 3 Ultra 550B A55B (Reasoning)

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
Gemini 3.5 Flash-Lite44#1/20 in End-to-End Response Time, #1/20 in Output Speed, #1/20 in Time per Intelligence Index Task
Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)7#1/20 in Humanity's Last Exam: Output Tokens per Task, #1/20 in AA-LCR v1.1: Output Tokens per Task, #3/20 in AA-LCR v1.1: Score
Gemini 3.8 Flash (high)60#1/11 in Speed, #1/11 in Speed, #2/20 in Output Speed
GPT-6 Astra (xhigh)15#1/20 in Terminal-Bench v4.0: Score, #2/20 in Humanity's Last Exam: Output Tokens per Task, #3/20 in AA-Omniscience Index: Score
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
gpt-oss-120b (high)39#1/20 in Cost to Run Artificial Analysis Intelligence Index, #1/20 in Cost to Run Artificial Analysis Intelligence Index, #1/20 in Humanity's Last Exam: Cost per Task
Muse Glimmer (high)43#1/20 in Output Tokens per Intelligence Index Task, #1/20 in Cost per Intelligence Index Task, #1/20 in Cost per Intelligence Index Task
DeepSeek V4.1 Flash (Reasoning, Max Effort)56#3/20 in End-to-End Response Time, #3/20 in Latency: Time To First Answer Token, #2/11 in Cost per Task
GPT-6 Astra (max)51#1/19 in MMMU-Pro: Score, #2/20 in AA-Omniscience Index, #2/20 in Artificial Analysis Intelligence Index by Open Weights / Proprietary
Muse Spark 1.3 (max)61#3/20 in AA-Briefcase Elo, #3/20 in Output Speed, #3/20 in GDPval-AA v2 Leaderboard
Nemotron 3 Ultra 550B A55B (Reasoning)46#1/12 in Artificial Analysis Openness Index: Score, #1/12 in Artificial Analysis Openness Index: Components, #2/20 in 𝜏³-Banking: Time per Task
Mistral Medium 3.541#2/20 in GDPval-AA v2: Output Tokens per Task, #3/20 in Output Tokens per Intelligence Index Task, #3/20 in Output Tokens per Intelligence Index Task
GPT-5.6 Terra (max)52#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
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)40#2/20 in SciCode: Score, #3/20 in AA-Omniscience Index, #3/20 in AA-Omniscience Index
MiniMax-M357#1/20 in AA-Omniscience Hallucination Rate, #1/20 in 𝜏³-Banking: Output Tokens per Task, #4/20 in Pricing: Cache Hit, Input, and Output
GPT-5.6 Luna (max)58#1/11 in Cost per Task, #1/11 in Cost per Task, #3/20 in Pricing: Cache Hit, Input, and Output
GPT-5.6 Sol (max)56#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
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, Xhigh Effort)11#4/20 in AA-Briefcase Rubric Pass Rate by File Type (Normalized), #4/20 in AA-Briefcase Elo, #4/20 in GDPval-AA v2 Leaderboard
DeepSeek V4 Pro 0813 (Reasoning, Max Effort)59#3/14 in Model Size: Total and Active Parameters, #3/12 in Artificial Analysis Openness Index: Score, #3/11 in Cost per Task

Metric reference

This ranking carries the metric Humanity's Last Exam time per task from the Humanity's Last Exam: Time per Task dataset in the tab::eval-hle 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 Humanity's Last Exam: Time per Task (family tab::eval-hle). 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-hle-humanity-s-last-exam-time-per-task.json. Free to reuse with attribution to AI Battle and the source dataset.

FAQ — Humanity's Last Exam: Time per Task

What is the best model for Humanity's Last Exam: Time per Task in 2026?

Gemini 3.5 Flash-Lite by Google currently leads the Humanity's Last Exam: Time per Task ranking with a score of 0.48, the highest value in this dataset across Frontier Evals. AI Battle aggregates the dataset from its public source and re-checks it daily.

How often is the Humanity's Last Exam: Time per Task ranking updated?

The Humanity's Last Exam: Time per Task 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 Humanity's Last Exam: Time per Task?

The top 3 are: 1. Gemini 3.5 Flash-Lite (0.48), 2. Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback) (0.89), 3. Gemini 3.8 Flash (high) (1.27).

All AI Battle Rankings

Directories