i was stuck on a landing page redesign with gpt 5.5 and opus 4.6 since a couple of days. gave a fresh try with opus 4.8 and it one shotted what i was looking for
Task A landing-page redesign GPT-5.5 and Opus 4.6 hadn't cracked over several days.
Anthropic · Claude Opus. Released May 28, 2026.
Claude Opus 4.8 is a model from Anthropic in the Claude Opus family, released May 28, 2026. evals.report tracks 30 reported Claude Opus 4.8 benchmark scores across SWE-bench Verified, GPQA Diamond, Humanity's Last Exam, DeepSWE, ARC-AGI-1, ARC-AGI-3, ARC-AGI-2, LiveBench, and 22 more — each shown with its benchmark, metric, source status, and date, and never combined into a single ranking.
| Benchmark | Category | Score | Metric | Status | Date | |
|---|---|---|---|---|---|---|
| SWE-bench Verified | Coding | 88.6% | % resolved | Verified | May 28, 2026 | Details |
| GPQA Diamond | Reasoning | 93.6% | accuracy | Verified | May 28, 2026 | Details |
| Humanity's Last Exam | Reasoning | 49.8% | accuracy | Verified | May 28, 2026 | Details |
| DeepSWE | Coding | 58% | % resolved | Verified | May 28, 2026 | Details |
| ARC-AGI-1 | Reasoning | 92% | accuracy | Official | May 28, 2026 | Details |
| ARC-AGI-3 | Reasoning | 1.52% | accuracy | Official | May 28, 2026 | Details |
| ARC-AGI-2 | Reasoning | 72.08% | accuracy | Official | May 28, 2026 | Details |
| LiveBench | Reasoning | 77.22% | score | Official | May 28, 2026 | Details |
| SWE-bench Pro | Coding | 69.2% | % resolved | Unverified | May 28, 2026 | Details |
| GBA Eval | Coding | 70.9% | overall score | Official | May 28, 2026 | Details |
| WeirdML | Coding | 82.9% | average accuracy | Official | May 28, 2026 | Details |
| CursorBench | Agents | 63.8% | score | Official | May 28, 2026 | Details |
| PostTrainBench | Agents | 37.23% | weighted average score | Official | May 28, 2026 | Details |
| Artificial Analysis Intelligence Index | Reasoning | 61 | Index | Official | May 28, 2026 | Details |
| OSWorld | Agents | 83.4% | task success rate | Verified | May 28, 2026 | Details |
| τ²-bench (Telecom) | Tool use | 94.4% | pass^1 | Official | May 28, 2026 | Details |
| AIME 2026 | Reasoning | 100.00% | accuracy | Official | May 28, 2026 | Details |
| GDPval | Agents | 1890 | Elo | Official | May 28, 2026 | Details |
| AA-Omniscience: Knowledge and Hallucination Benchmark | Reasoning | 27 | AA-Omniscience Index | Official | May 28, 2026 | Details |
| IFBench | Reasoning | 62.2% | accuracy | Official | May 28, 2026 | Details |
| EQ-Bench Creative Writing v3 | Chat preference | 2031 | Elo | Verified | May 28, 2026 | Details |
| Design Arena | Chat preference | 1282 | Elo | Verified | May 28, 2026 | Details |
| CharXiv | Multimodal | 89.9% | accuracy | Unverified | May 28, 2026 | Details |
| ScreenSpot-Pro | Multimodal | 87.9% | accuracy | Unverified | May 28, 2026 | Details |
| SWE-bench Multimodal | Coding | 38.4% | % resolved | Verified | May 28, 2026 | Details |
| MathArena HMMT February 2026 | Reasoning | 95.45% | accuracy | Official | May 28, 2026 | Details |
| Vibe Code Bench | Coding | 82.72% | Overall accuracy | Official | May 28, 2026 | Details |
| Remote Labor Index | Agents | 8.33% | automation rate | Official | May 28, 2026 | Details |
| FrontierSWE | Agents | 75% | dominance score | Official | May 28, 2026 | Details |
| FrontierCode | Coding | 13.4% | weighted score (Diamond) | Official | May 28, 2026 | Details |
Real-world feedback on Claude Opus 4.8 from people using it on actual prompts — praise and criticism alike, each linked to its source. Qualitative, never scored.
Report tone
Report type
Topic
i was stuck on a landing page redesign with gpt 5.5 and opus 4.6 since a couple of days. gave a fresh try with opus 4.8 and it one shotted what i was looking for
Task A landing-page redesign GPT-5.5 and Opus 4.6 hadn't cracked over several days.
I think in terms of application functionality, quality, and design, Opus won … got stuck twice in a retry loop (had to prompt to self-correct).
Task Head-to-head vs Sakana Fugu Ultra: a single-file Three.js Crossy Road game.
Opus 4.8 in the last 48hrs is amazing … it's just very sad to go from godlike performance to barely usable some days.