Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 3 models | Unknowngemma-3-4b-itRemove × | anthropicAnthropic: Claude Opus 5.5Remove × | reflectionReflection: Beam 1.0 501B A23BRemove × |
|---|---|---|---|
| What’s different | 131.1K context · 118K max output · Structured output | Always-on adaptive thinking defaults to medium effort; built for sustained work across large codebases and professional documents. | Apache-2.0 text model with 501B total and 23B active parameters; ships BF16, FP8 and NVFP4 weights. |
| Date | Oct 16, 2026Discovered | Sep 22, 2026Released | Oct 16, 2026Released |
API prices USD · provider configuration shown below | |||
| Listed rate | $0.05 in / $0.10 out/ 1M tokensExperiential · all routes ↗Standard list rate | $4.00 in / $20.00 out/ 1M tokensAmazon Bedrock · via OpenRouter · all routes ↗amazon-bedrock | $0.25 in / $1.00 out/ 1M tokensNebius · via OpenRouter · all routes ↗nebius/fp8 · quantization=fp8 |
| Provider endpoints | 1 endpoint → | 14 endpoints → | 6 endpoints → |
Benchmarks Each result retains its evaluation configuration | |||
| AA Intelligence ↗4.3.2 | Not reported | 57.62 ↗Effort: max · Max, Default FallbackIndependent result | 30.33 ↗Effort not specifiedIndependent result |
| AA-Briefcase ↗1.1 | Not reported | 1,802.36 ↗Effort: max · Max, Default FallbackIndependent result | 976.2 ↗Effort not specifiedIndependent result |
| GDPval-AA ↗2.1 | Not reported | 1,866.27 ↗Effort: max · Max, Default FallbackIndependent result | 1,177.08 ↗Effort not specifiedIndependent result |
| AutomationBench-AA ↗AA Index 4.3.2 collection | Not reported | 69.54% ↗Effort: max · Max, Default FallbackIndependent result | 48.46% ↗Effort not specifiedIndependent result |
| Terminal-Bench 4.0 · AA ↗ | Not reported | 59.6% ↗Effort: max · Max, Default FallbackHarness unreportedIndependent result | 3.03% ↗Effort not specifiedHarness unreportedIndependent result |
| SciCode ↗AA Index 4.3.2 collection | Not reported | 66.9% ↗AA · Under reviewEffort: max · Max, Default FallbackIndependent result | 48.5% ↗AA · Under reviewEffort not specifiedIndependent result |
| Humanity’s Last Exam ↗AA Index 4.3.2 collection | Not reported | 61.35% ↗Effort: max · Max, Default FallbackIndependent result | 34.66% ↗Effort not specifiedIndependent result |
| GDP.pdf ↗AA Index 4.3.2 collection | Not reported | 26.2% ↗Effort: max · Max, Default FallbackIndependent result | 11.6% ↗Effort not specifiedIndependent result |
| CritPt ↗AA Index 4.3.2 collection | Not reported | 31.71% ↗AA · Under reviewEffort: max · Max, Default FallbackIndependent result | 13.14% ↗AA · Under reviewEffort not specifiedIndependent result |
| AA-Omniscience ↗AA Index 4.3.2 collection | Not reported | 46.42 ↗Effort: max · Max, Default FallbackIndependent result | 1.5 ↗Effort not specifiedIndependent result |
| AA-LCR ↗1.1 | Not reported | 84.67% ↗Effort: max · Max, Default FallbackIndependent result | 78% ↗Effort not specifiedIndependent result |
| LiveBench ↗2.0 · 2026-10-14 (dataset 2026-09-02) | Not reported | 86.53% ↗Effort: max · single run · equal mean of 7 suitesIndependent result | 55.5% ↗Effort: max · single run · equal mean of 7 suitesIndependent result |
| LiveBench Design ↗2.0 · 2026-10-14 (dataset 2026-09-02) | Not reported | 86.9% ↗Effort: max · single runIndependent result | 67.9% ↗Effort: max · single runIndependent result |
| LiveBench Research ↗2.0 · 2026-10-14 (dataset 2026-09-02) | Not reported | 85% ↗Effort: max · single runIndependent result | 72.8% ↗Effort: max · single runIndependent result |
| LiveBench Browser Use ↗2.0 · 2026-10-14 (dataset 2026-09-02) | Not reported | 80% ↗Effort: max · single runIndependent result | 0% ↗Effort: max · single runIndependent result |
| LiveBench Coding ↗2.0 · 2026-10-14 (dataset 2026-09-02) | Not reported | 96.3% ↗Effort: max · single runIndependent result | 83.9% ↗Effort: max · single runIndependent result |
| LiveBench Agentic ↗2.0 · 2026-10-14 (dataset 2026-09-02) | Not reported | 85% ↗Effort: max · single runIndependent result | 17.3% ↗Effort: max · single runIndependent result |
| LiveBench Data Analysis ↗2.0 · 2026-10-14 (dataset 2026-09-02) | Not reported | 80.3% ↗Effort: max · single runIndependent result | 66.4% ↗Effort: max · single runIndependent result |
| LiveBench Reasoning ↗2.0 · 2026-10-14 (dataset 2026-09-02) | Not reported | 92.2% ↗Effort: max · single runIndependent result | 80.2% ↗Effort: max · single runIndependent result |
Specifications | |||
| Context window | 131.1K | 1M | 1M |
| Max output | 118K | 128K | 943.7K |
| Parameters | — | — | 501B |
| Tool calling | Not reported | Supported | Supported |
| Structured output | Supported | Supported | Supported |
| Image input | Not reported | Supported | Not reported |
| Reasoning | Not reported | Supported | Supported |
| Prompt caching | Not reported | Supported | Supported |
| Open weights | Not reported | Not reported | Supported |