Agent Arena: Kimi K3 offers best value, Claude Opus 5 is priciest
arena · x · 2026-08-20
Agent Arena data reveals a 5x cost variance among top models: Kimi K3 (Max) ranks #4 with the lowest cost ($0.62/task), while Claude Opus 5 (Max) is the priciest ($3.37/task). Grok and Qwen deliver competitive performance at low costs. The evaluation covers millions of real-world agentic tasks.
More from coding & agent
- atuin v18.24 adds cross-device sync to resume AI threads across Claude and Codex — braelyn_ai · 2026-10-16
- Agents turn conservative as context grows: edits shrink from 150 to 30 lines — dbreunig · 2026-10-16
- ai& becomes an official built-in Cline provider with 13 open-weight models — DavidBennett__ · 2026-10-16
- Open-source rizin-mcp lets LLMs run local binary and malware analysis via Rizin — Pure_Emergency1424 · 2026-10-16
- x402 as a free GTM channel: agents discover 100+ tools, no API keys needed — 0xJeff · 2026-10-16
- Sam Altman: stop getting better at prompts, build loops and graphs that prompt for you — goyalshaliniuk · 2026-10-16