AI Battle > Rankings > Time per Task
null by null leads the Time per Task ranking with a score of 703. The ranking covers 10 evaluated coding agents from a public dataset that AI Battle re-checks daily.
Last updated: . Source: public benchmark datasets and provider pricing, aggregated daily; 10 entries shown.
| # | Entry | Creator | Value | Δ vs #1 |
|---|---|---|---|---|
| 1 | Antigravity SDK - Gemini 3.8 Flash (high) (Google) | 703 | 0.0% | |
| 2 | Muse Code - Muse Spark 1.3 (max) (Meta) | 1107 | 57.5% | |
| 3 | Grok Build - Grok 4.6 (xhigh) (SpaceXAI) | 1167 | 66.1% | |
| 4 | Codex - GPT-6 Astra (max) ({'reasoning_effort': 'max'}) (OpenAI) | 1764 | 151.0% | |
| 5 | Claude Code - Fable 5.1 (max) (with fallback) (Anthropic) | 2090 | 197.4% | |
| 6 | Codex - DeepSeek V4 Pro 0813 (max) (DeepSeek) | 2416 | 243.8% | |
| 7 | Claude Code - Opus 5 (max) (Anthropic) | 2512 | 257.5% | |
| 8 | Opencode - GLM-5.3 ({'reasoning_effort': 'max'}) (Z.ai) | 2888 | 311.0% | |
| 9 | Kimi Code CLI - Kimi K3 (Moonshot AI) | 3689 | 425.0% | |
| 10 | Claude Code - Qwen3.8 Max (Alibaba Cloud) | 3785 | 438.6% |
Across the 10 numeric entries in this window the median is 2253 and the mean is 2212, so the typical entry sits 1550 above the leader. The window spans 703 to 3785.
5 of 10 entries are at or above the median, and the top three hold 47% of the combined value — read it against the metric below, since a higher number is not "better" for every dataset.
The source dataset for this family does not publish a provider or creator label per entry, so AI Battle cannot group them: the table above is the complete published list. Where the dataset does carry a label (model, gateway and tool families do), this section names the creators and how many entries each holds.
This ranking carries the metric
codingAgentsMeanAgentWallTimeSec from the
Time per Task dataset in the tab::agents-coding 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.
Rebuilt on from the
public dataset Time per Task (family tab::agents-coding).
The source lists 10 entries and all 10 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.
Machine-readable copy of this table, with the statistics below and the source provenance: /data/rankings/agents-coding-time-per-task.json. Free to reuse with attribution to AI Battle and the source dataset.
null by null currently leads the Time per Task ranking with a score of 703, the highest value in this dataset across Coding Agents. AI Battle aggregates the dataset from its public source and re-checks it daily.
The 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.
The top 3 are: 1. null (703), 2. null (1107), 3. null (1167).