Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 3 models | xiaomiXiaomi: MiMo-V2.6-ProRemove × | openaiOpenAI: GPT-6.1 SolRemove × | anthropicAnthropic: Claude Opus 5.5Remove × |
|---|---|---|---|
| What’s different | MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding... | Requires Responses API for tools; offers Ultrafast inference with US or EU data residency. | Always-on adaptive thinking defaults to medium effort; built for sustained work across large codebases and professional documents. |
| Date | Sep 21, 2026Released | Sep 29, 2026Released | Sep 22, 2026Released |
API prices USD · provider configuration shown below | |||
| Listed rate | $0.387 in / $0.783 out/ 1M tokensDeepInfra · via OpenRouter · all routes ↗deepinfra/fp8 · quantization=fp8 | $1.00 in / $5.00 out/ 1M tokensOpenAI · via OpenRouter · all routes ↗openai/flex · tier=flex · prompt ≤ 272000 tokens | $4.00 in / $20.00 out/ 1M tokensAmazon Bedrock · via OpenRouter · all routes ↗amazon-bedrock |
| Provider endpoints | 7 endpoints → | 10 endpoints → | 14 endpoints → |
Benchmarks Each result retains its evaluation configuration | |||
| AA Intelligence ↗4.3.2 | 46.32 ↗Effort not specifiedIndependent result | 51.83 ↗Effort: max · MaxIndependent result | 57.62 ↗Effort: max · Max, Default FallbackIndependent result |
| AA-Briefcase ↗1.1 | 1,513.98 ↗Effort not specifiedIndependent result | 1,556.34 ↗Effort: max · MaxIndependent result | 1,802.36 ↗Effort: max · Max, Default FallbackIndependent result |
| GDPval-AA ↗2.1 | 1,683.29 ↗Effort not specifiedIndependent result | 1,592.1 ↗Effort: max · MaxIndependent result | 1,866.27 ↗Effort: max · Max, Default FallbackIndependent result |
| AutomationBench-AA ↗AA Index 4.3.2 collection | 58.62% ↗Effort not specifiedIndependent result | 64.87% ↗Effort: max · MaxIndependent result | 69.54% ↗Effort: max · Max, Default FallbackIndependent result |
| Terminal-Bench 4.0 · AA ↗ | 34.85% ↗Effort not specifiedHarness unreportedIndependent result | 56.06% ↗Effort: max · MaxHarness unreportedIndependent result | 59.6% ↗Effort: max · Max, Default FallbackHarness unreportedIndependent result |
| SciCode ↗AA Index 4.3.2 collection | 60.88% ↗AA · Under reviewEffort not specifiedIndependent result | 54.17% ↗AA · Under reviewEffort: max · MaxIndependent result | 66.9% ↗AA · Under reviewEffort: max · Max, Default FallbackIndependent result |
| Humanity’s Last Exam ↗AA Index 4.3.2 collection | 49.35% ↗Effort not specifiedIndependent result | 52.92% ↗Effort: max · MaxIndependent result | 61.35% ↗Effort: max · Max, Default FallbackIndependent result |
| GDP.pdf ↗AA Index 4.3.2 collection | 19.2% ↗Effort not specifiedIndependent result | 31% ↗Effort: max · MaxIndependent result | 26.2% ↗Effort: max · Max, Default FallbackIndependent result |
| CritPt ↗AA Index 4.3.2 collection | 26.57% ↗AA · Under reviewEffort not specifiedIndependent result | 31.71% ↗AA · Under reviewEffort: max · MaxIndependent result | 31.71% ↗AA · Under reviewEffort: max · Max, Default FallbackIndependent result |
| AA-Omniscience ↗AA Index 4.3.2 collection | 8.38 ↗Effort not specifiedIndependent result | 41.53 ↗Effort: max · MaxIndependent result | 46.42 ↗Effort: max · Max, Default FallbackIndependent result |
| AA-LCR ↗1.1 | 86.33% ↗Effort not specifiedIndependent result | 83% ↗Effort: max · MaxIndependent result | 84.67% ↗Effort: max · Max, Default FallbackIndependent result |
| LiveBench ↗2.0 · 2026-10-14 (dataset 2026-09-02) | 74.87% ↗Effort: high · single run · equal mean of 7 suitesIndependent result | 85.41% ↗Effort: max · single run · equal mean of 7 suitesIndependent result | 86.53% ↗Effort: max · single run · equal mean of 7 suitesIndependent result |
| LiveBench Design ↗2.0 · 2026-10-14 (dataset 2026-09-02) | 78.5% ↗Effort: high · single runIndependent result | 82.1% ↗Effort: max · single runIndependent result | 86.9% ↗Effort: max · single runIndependent result |
| LiveBench Research ↗2.0 · 2026-10-14 (dataset 2026-09-02) | 76.7% ↗Effort: high · single runIndependent result | 83.5% ↗Effort: max · single runIndependent result | 85% ↗Effort: max · single runIndependent result |
| LiveBench Browser Use ↗2.0 · 2026-10-14 (dataset 2026-09-02) | 88% ↗Effort: high · single runIndependent result | 88% ↗Effort: max · single runIndependent result | 80% ↗Effort: max · single runIndependent result |
| LiveBench Coding ↗2.0 · 2026-10-14 (dataset 2026-09-02) | 81.5% ↗Effort: high · single runIndependent result | 96% ↗Effort: max · single runIndependent result | 96.3% ↗Effort: max · single runIndependent result |
| LiveBench Agentic ↗2.0 · 2026-10-14 (dataset 2026-09-02) | 47.5% ↗Effort: high · single runIndependent result | 73% ↗Effort: max · single runIndependent result | 85% ↗Effort: max · single runIndependent result |
| LiveBench Data Analysis ↗2.0 · 2026-10-14 (dataset 2026-09-02) | 72.3% ↗Effort: high · single runIndependent result | 82.7% ↗Effort: max · single runIndependent result | 80.3% ↗Effort: max · single runIndependent result |
| LiveBench Reasoning ↗2.0 · 2026-10-14 (dataset 2026-09-02) | 79.6% ↗Effort: high · single runIndependent result | 92.6% ↗Effort: max · single runIndependent result | 92.2% ↗Effort: max · single runIndependent result |
Specifications | |||
| Context window | 1.1M | 1.1M | 1M |
| Max output | 131.1K | 128K | 128K |
| Parameters | — | — | — |
| Tool calling | Supported | Supported | Supported |
| Structured output | Supported | Supported | Supported |
| Image input | Supported | Supported | Supported |
| Audio input | Supported | Not reported | Not reported |
| Video input | Supported | Not reported | Not reported |
| Reasoning | Supported | Supported | Supported |
| Prompt caching | Supported | Supported | Supported |
| Open weights | Supported | Not reported | Not reported |