GoldieBench deep dive
Opus 4.8's full benchmark breakdown.
The reasoning king — deepest thinking, premium price. Every number below is either one of my own judged one-shot builds - playable on this site - or an outside result with its source linked. Nothing display-only, nothing vibes.
01 · The headline numbers
02 · Every benchmark, bar by bar
All 47 scored tasks, best first. Hover for the judge's comment; click through for every model's build on that task. Or overlay other models in the interactive graphs.
03 · Where it wins - with the judge's own words
“Opus nailed it — a pure-black event horizon, a bright photon ring, and the disk bent up and over the top exactly like the film's lensing. GLM came in strong with a clean ring and a starfield warping past the hole. Kimi's disk is fine, but the background is a soft grey blur instead of stars. This one's Opus's.”
“Funniest result of the lot: GLM and Opus independently produced near-identical premium 'Introducing Nova 1 — Intelligence, reimagined / distilled' keynote pages — gradient hero, full nav, pricing tiers. A dead heat. Kimi's was a plainer set of feature cards.”
“Opus nailed the brief — labelled planet orbits, a real NEO / close-pass panel, a sim clock. GLM went for drama: a glowing nebula swirl that's gorgeous but reads more galaxy than orbit map. Kimi's is accurate but dim and sparse.”
“All three are real, playable shooters. Opus drops you in a corridor with an imp dead ahead — gun, crosshair and HUD framed like a screenshot. Kimi matches it: a monster down a textured hall, health, ammo, minimap. GLM ships a gorgeous 'HAZARD PROTOCOL' title screen with a working game behind it, though it too spawns facing a wall. Opus by a hair on the cleanest fight.”
04 · Where it struggles - quoted, not hidden
Boards that hide the weak rows are brochures. These are Opus 4.8's lowest scored builds, verdicts unedited:
“16KB · animation runs but no input response · plain”
“9KB · animation runs but no input response · plain”
“14KB · animation runs but no input response · webgl, bloom”
“13KB · animation runs but no input response · webgl”
05 · Category breakdown vs the whole field
Games (23 tasks)
Others (0 tasks)
Pages (3 tasks)
Sims (12 tasks)
Visuals (9 tasks)
06 · Outside signals - every row sourced
My bench measures one thing: judged one-shot builds. These outside rows measure other things - kept separate, never blended into the GoldieBench average, every value linked to where it comes from.
Vendor-published numbers
| Benchmark | Result | Source |
|---|---|---|
| SWE-bench Verified | 88.6% | www.anthropic.com |
| SWE-bench Pro | 69.2% (+4.9 over Opus 4.7) | www.anthropic.com |
| Terminal-Bench 2.1 | 74.6% (+8.5 over Opus 4.7) | www.anthropic.com |
| GDPval-AA | 1890 Elo - 121 ahead of GPT-5.5 at release | www.anthropic.com |
| Pricing | $5/M input - $25/M output, unchanged from 4.7 | www.anthropic.com |
From the source guides
| Measure | Result | Source guide |
|---|---|---|
| SWE-bench Verified | 88.6% | /three-dragons |
07 · Head-to-head records
08 · Methodology + honest limits
Every GoldieBench score is a one-shot, single-file build from an identical prompt - no retries, no hand-fixing - rendered for real, screenshotted, and scored 0-10 by one judge model on one rubric across the whole field. Failures score as failures. What this bench does NOT measure: multi-turn agent work, long-context recall, or API latency - that is what the sourced outside rows are for. Full method: /methodology.
Frequently asked questions
01How does Opus 4.8 perform on GoldieBench?
Opus 4.8 averages 7.51/10 across 47 scored one-shot build tasks, ranking #12 of 17 ranked frontier models, with 3 task golds, 1 silvers and 2 bronzes. Every score is a real judged build you can open and play on this site.
02What is Opus 4.8 best at?
Its strongest scored build is Blackhole at 9.0/10. By category it averages Game 7.4, Page 7.2, Sim 7.8, Visual 7.4 on the bench.
03How much does Opus 4.8 cost?
Premium pricing via the Anthropic API: $15 per million input tokens, $75 per million output tokens. Extended thinking is included but adds latency.
Source ledger
- 01Official vendor site: anthropic.com/claudewww.anthropic.com
- 02SWE-bench Verifiedwww.anthropic.com
- 03SWE-bench Verifiedagentos.guide
- 04Julian's guide: /opus-ultracodeagentos.guide
- 05Julian's guide: /claude-fable-5agentos.guide
- 06Julian's guide: /glm-vs-kimi-vs-opusagentos.guide
- 07Julian's guide: /glm-vs-qwen-vs-opusagentos.guide
Every model's breakdown
Run this stack yourself.
Every demo on this bench was built inside the Agent Operating System — one prompt, one shot, single HTML file out. The Agent OS, the prompts, the templates, the weekly walkthroughs and 4,000+ founders shipping with it every day all live inside the AI Profit Boardroom.