Claude Opus 4.8vsKimi K3
1 prompt where both models ran the exact same instructions. Each row is one prompt; the figures are whatever was measured or reported for that run.
Claude Opus 4.8 and Kimi K3 ran the same prompt on 1 task, side by side. Cost, duration and outcome for each — 0 measured locally, no aggregate score.
- Shared prompts
- 1
- Compared
- models
- Measured runs
- 0
No winner is declared. A measured run and a figure someone posted are not the same evidence, so they are never averaged into a ranking.
What this page shows, and how to read it
Claude Opus 4.8 is a large language model from Anthropic. No harness is recorded for its runs below. Kimi K3 is a large language model from Moonshot AI. No harness is recorded for its runs below.
The two sides share 1 prompt on this site: "Besiege Earth — low-poly planet in one HTML file". It is a games prompt, rated hard, published by Terry Chen on Jul 28, 2026, tagged 3d, threejs, single-file, procedural and one-shot. Every run has a video capture on the prompt page. Across it, Claude Opus 4.8 completed its run, and Kimi K3 completed its run. Claude Opus 4.8 has a reported duration of 1m 40s. Kimi K3 has a reported duration of 5m 06s.
How to read the outcomes. Completed means the prompt alone produced a working artefact. Failed means this run did not — the build broke, the result would not run, or the agent stopped short of a working state. That is a fact about one run on one prompt, not a verdict on the tool: the same programs complete other prompts elsewhere on this site. Timed out means the run was cut at its time limit with the artefact unfinished, so whatever it cost bought a partial result. Stopped and Interrupted mark runs ended from the outside before they concluded. A low cost attached to a run that did not finish is not a saving — it is the price of an attempt, which is why every figure on this page travels with its status.
Every figure above carries a trust label. Measured means SamePrompt ran it locally in Bench Arena, reconciled the tokens on the harness log and recomputed the cost from them. Reported means the author of the source announced the figure; it is shown as stated and cannot be verified here. The two are never summed, averaged or ranked, and this page declares no winner: a cheap run that failed and an expensive run that completed are two facts, not a score.