Get the Agent OS + join 4,000+ founders inside the AI Profit Boardroom → Join AIPB ($59/mo)

GoldieBench deep dive

MiniMax M3's full benchmark breakdown.

1M-context frontier model at $0.30/M tokens — cheapest big-context model on the bench. 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.

Data refreshed
2026-07-17
Scored tasks
47
Reading time
10 min
External sources
5

01 · The headline numbers

GoldieBench average
7.97/10
47 scored one-shot tasks
Board rank
#7
of 17 ranked frontier models
Task medals
2🥇 3🥈 7🥉
outright wins on shared briefs
Context
1,048,576-token context — matches GLM-5.2 and Fable 5
$0.30 / 1M input tokens, $1.50 / 1M output

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

“34KB frozen open world — snowy mountains, pines, flying dragon, full HUD.”

- the judge's verdict, unedited

“41KB Nordic crypt with torch-lit corridors, chasing skeletons, boss room.”

- the judge's verdict, unedited

“59KB third-person arcade racer. Banking turns, speed boost, drift, lap timer.”

- the judge's verdict, unedited

“31KB Gray-Scott shader with click-to-seed.”

- the judge's verdict, unedited

“95KB · plays clean · rAF”

- the judge's verdict, unedited

04 · Where it struggles - quoted, not hidden

Boards that hide the weak rows are brochures. These are MiniMax M3's lowest scored builds, verdicts unedited:

“Minimal 1KB plasma. Brief is barely met.”

- the judge's verdict, unedited

“Canvas-2D raycaster — WASD walking, textured walls, distance fog.”

- the judge's verdict, unedited

“Minimal gravitational-lens shader.”

- the judge's verdict, unedited

“3D tunnel flythrough with distorted starfield.”

- the judge's verdict, unedited

05 · Category breakdown vs the whole field

Games (23 tasks)

MiniMax M38.2
field avg7.1

Others (0 tasks)

field avg7.4

Pages (3 tasks)

MiniMax M38.2
field avg7.5

Sims (12 tasks)

MiniMax M37.9
field avg6.7

Visuals (9 tasks)

MiniMax M37.4
field avg6.7

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

BenchmarkResultSource
SWE-bench Pro59.0% - vendor-run with agent scaffoldingwww.marktechpost.com
Terminal-Bench 2.166.0%www.marktechpost.com
BrowseComp83.5 - above Opus 4.7's 79.3felloai.com
MMMU-Pro (multimodal)78.1%felloai.com

Independent evaluations

BenchmarkResultSource
Verification statusseveral results ran on MiniMax's own infrastructure with scaffolding; independent verification pendingwww.techtimes.com

From the source guides

MeasureResultSource guide
Context window1,048,576 tokens/openrouter
Per-token cost$0.30 / M input · $1.50 / M output/openrouter

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 MiniMax M3 perform on GoldieBench?

MiniMax M3 averages 7.97/10 across 47 scored one-shot build tasks, ranking #7 of 17 ranked frontier models, with 2 task golds, 3 silvers and 7 bronzes. Every score is a real judged build you can open and play on this site.

02What is MiniMax M3 best at?

Its strongest scored build is Dragonrealm at 9.0/10. By category it averages Game 8.2, Page 8.2, Sim 7.9, Visual 7.4 on the bench.

03How much does MiniMax M3 cost?

MiniMax M3 is the cheapest 1M-context frontier model on the bench — roughly 1/200th the per-call cost of OpenRouter Fusion and 1/30th of Claude Opus 4.8. Designed for high-volume agent workloads where context length matters but per-call budget is tight.

Source ledger

  1. 01Official vendor site: minimax.iowww.minimax.io
  2. 02SWE-bench Prowww.marktechpost.com
  3. 03BrowseCompfelloai.com
  4. 04Verification statuswww.techtimes.com
  5. 05Context windowagentos.guide

Every model's breakdown

The same stack Julian uses

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.

4,000+founders
258documented wins
38countries
$59/momonthly