<p>Anthropic&#39;s Claude Opus 4.8 was released yesterday. We tested it on both <a href="https://www.mercor.space/apex/apex-agents-leaderboard/" target="_blank" rel="noopener noreferrer" class="text-indigo-600">APEX-Agents</a> and <a href="https://www.mercor.space/apex/apex-swe-leaderboard/" target="_blank" rel="noopener noreferrer" class="text-indigo-600">APEX-SWE</a> ahead of the launch. Here&#39;s how it performed.</p>
<img src="https://cdn.sanity.io/images/h6s14f4z/production/86359879fe8e98a24b77bcf1b2bcf6586dc55629-1580x1346.png" alt="Claude Opus 4.8 on the APEX-SWE leaderboard" style="width: 100%; border-radius: 10px;" />
<img src="https://cdn.sanity.io/images/h6s14f4z/production/ec63174df8628e048e2f42bc8f900a9807b0b27c-1750x2004.jpg" alt="Claude Opus 4.8 APEX-SWE domain results" style="width: 100%; border-radius: 10px;" />
<img src="https://cdn.sanity.io/images/h6s14f4z/production/2ccefa03f2328af6eb02bcf0266e47f749b1dbb0-1580x1664.png" alt="Claude Opus 4.8 on the APEX-Agents leaderboard" style="width: 100%; border-radius: 10px;" />
<img src="https://cdn.sanity.io/images/h6s14f4z/production/20cb595d44876b6c4c557f825abaa3c2697d78f3-3426x2532.png" alt="Claude Opus 4.8 APEX-Agents results by domain" style="width: 100%; border-radius: 10px;" />
<img src="https://cdn.sanity.io/images/h6s14f4z/production/d690f509df4ac9b8ab64022ec7c9483d744468fb-2574x1961.png" alt="Claude Opus 4.8 token usage on APEX-Agents" style="width: 100%; border-radius: 10px;" />

Anthropic's Claude Opus 4.8 was released yesterday. We tested it on APEX-Agents and APEX-SWE ahead of the launch.

Claude Opus 4.8 tops APEX-SWE leaderboard

Opus 4.8

Claude Opus 4.8 tops APEX-SWE, places 2nd on APEX-Agents

Find out how well frontier AI models perform economically viable work

APEX Benchmarks

APEX-Accounting

Opus 5

Grok 4.5 and GPT-5.6 Sol

Fable 5 Re-Release

Sonnet 5

Claude Fable 5

Gemini 3.5 Flash

Model releases