Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 3 models | MiniMaxAIMiniMax-M3Remove × | stepfun-aiStep-5-PreviewRemove × | Briaremove_background_guidedRemove × |
|---|---|---|---|
| What’s different | MiniMax-M3 is a native multimodal model with 1M context. It has ~428B parameters and ~23B activated parameters. | 600B total and 27B active parameters; accepts images and video, with FP8 and BF16 weights for deployment. | Prompt-guided background removal by Bria: tell it what to keep or what to remove and get a clean cutout with true transparency, at the original resolution with the original pixels untouched. Trained… |
| Date | Jun 1, 2026Released | Sep 18, 2026Released | Oct 14, 2026Listed |
API prices USD · provider configuration shown below | |||
| Listed rate | $0.28 in / $1.10 out/ 1M tokensdeepinfra · via Hugging Face · all routes ↗ | $1.00 in / $2.70 out/ 1M tokensDeepInfra · all routes ↗ | See provider quotes |
| Provider endpoints | 7 endpoints → | 6 endpoints → | 0 endpoints → |
Benchmarks Each result retains its evaluation configuration | |||
| AA Intelligence ↗4.3.2 | 29.22 ↗Effort not specifiedIndependent result | 43.73 ↗Effort not specifiedIndependent result | Not reported |
| AA-Briefcase ↗1.1 | 1,090.37 ↗Effort not specifiedIndependent result | 1,424.32 ↗Effort not specifiedIndependent result | Not reported |
| GDPval-AA ↗2.1 | 1,242.47 ↗Effort not specifiedIndependent result | 1,586.63 ↗Effort not specifiedIndependent result | Not reported |
| AutomationBench-AA ↗AA Index 4.3.2 collection | 21.25% ↗Effort not specifiedIndependent result | 50.96% ↗Effort not specifiedIndependent result | Not reported |
| Terminal-Bench 4.0 · AA ↗ | 2.02% ↗Effort not specifiedHarness unreportedIndependent result | 33.33% ↗Effort not specifiedHarness unreportedIndependent result | Not reported |
| SciCode ↗AA Index 4.3.2 collection | 47.11% ↗AA · Under reviewEffort not specifiedIndependent result | 58.91% ↗AA · Under reviewEffort not specifiedIndependent result | Not reported |
| Humanity’s Last Exam ↗AA Index 4.3.2 collection | 38.97% ↗Effort not specifiedIndependent result | 46.48% ↗Effort not specifiedIndependent result | Not reported |
| GDP.pdf ↗AA Index 4.3.2 collection | 9.8% ↗Effort not specifiedIndependent result | 14.8% ↗Effort not specifiedIndependent result | Not reported |
| CritPt ↗AA Index 4.3.2 collection | 3.71% ↗AA · Under reviewEffort not specifiedIndependent result | 20.86% ↗AA · Under reviewEffort not specifiedIndependent result | Not reported |
| AA-Omniscience ↗AA Index 4.3.2 collection | 1.35 ↗Effort not specifiedIndependent result | 16.38 ↗Effort not specifiedIndependent result | Not reported |
| AA-LCR ↗1.1 | 83% ↗Effort not specifiedIndependent result | 88.33% ↗Effort not specifiedIndependent result | Not reported |
| LiveBench ↗2.0 · 2026-10-14 (dataset 2026-09-02) | Not reported | 62.01% ↗Effort: max · single run · equal mean of 7 suitesIndependent result | Not reported |
| LiveBench Design ↗2.0 · 2026-10-14 (dataset 2026-09-02) | Not reported | 76.9% ↗Effort: max · single runIndependent result | Not reported |
| LiveBench Research ↗2.0 · 2026-10-14 (dataset 2026-09-02) | Not reported | 72.8% ↗Effort: max · single runIndependent result | Not reported |
| LiveBench Browser Use ↗2.0 · 2026-10-14 (dataset 2026-09-02) | Not reported | 24% ↗Effort: max · single runIndependent result | Not reported |
| LiveBench Coding ↗2.0 · 2026-10-14 (dataset 2026-09-02) | Not reported | 85.6% ↗Effort: max · single runIndependent result | Not reported |
| LiveBench Agentic ↗2.0 · 2026-10-14 (dataset 2026-09-02) | Not reported | 27.5% ↗Effort: max · single runIndependent result | Not reported |
| LiveBench Data Analysis ↗2.0 · 2026-10-14 (dataset 2026-09-02) | Not reported | 63.5% ↗Effort: max · single runIndependent result | Not reported |
| LiveBench Reasoning ↗2.0 · 2026-10-14 (dataset 2026-09-02) | Not reported | 83.8% ↗Effort: max · single runIndependent result | Not reported |
Specifications | |||
| Context window | 1M | 1M | — |
| Max output | — | 64K | — |
| Parameters | — | — | — |
| Tool calling | Supported | Supported | Not reported |
| Structured output | Supported | Supported | Not reported |
| Image input | Supported | Supported | Not reported |
| Video input | Not reported | Supported | Not reported |
| Reasoning | Supported | Supported | Not reported |
| Prompt caching | Not reported | Supported | Not reported |
| Open weights | Supported | Supported | Not reported |