OutYet.ai
OutYet.ai
Benchmarks
Compare AI models
Pick two models to see release dates, benchmark scores, and community ratings side by side.
Frontier benchmarks
Frontier board
6 releases. Five ways to compare.
Selected for recent releases and benchmark coverage, not a single overall rank. Each column sorts the same models by its own score. No reading means no bar.
○ Independent evaluation · ◆ Vendor or self-reported, labeled per reading.
Coding
BenchLM · 0 to 100
- Claude Opus 5.582.82Independent
Anthropic
- Claude Fable 5.176.58Independent
Anthropic
- GPT-6 Astra74.83Independent
OpenAI
- Gemini 4 Argon72.24Independent
Google DeepMind
- GPT-6.1 Sol70.39Independent
OpenAI
- Gemini 3.8 Flash60.02Independent
Google DeepMind
Agentic
BenchLM · 0 to 100
- Claude Opus 5.589.3Independent
Anthropic
- Claude Fable 5.180.15Independent
Anthropic
- Gemini 4 Argon77.66Independent
Google DeepMind
- GPT-6.1 Sol75.84Independent
OpenAI
- GPT-6 Astra73.33Independent
OpenAI
- Gemini 3.8 Flash64.26Independent
Google DeepMind
Reasoning
BenchLM · 0 to 100
- GPT-6 Astra91.6Independent
OpenAI
- GPT-6.1 Sol88.8Independent
OpenAI
- Gemini 4 Argon85.2Independent
Google DeepMind
- Claude Opus 5.584.4Independent
Anthropic
- Claude Fable 5.183.5Independent
Anthropic
- Gemini 3.8 Flash72.6Independent
Google DeepMind
Knowledge
BenchLM · 0 to 100
- Claude Opus 5.589.36Independent
Anthropic
- GPT-6.1 Sol85.95Independent
OpenAI
- Claude Fable 5.185.85Independent
Anthropic
- GPT-6 Astra85.51Independent
OpenAI
- Gemini 4 Argon80.55Independent
Google DeepMind
- Gemini 3.8 Flash69.8Independent
Google DeepMind
Arena
LM Arena · Elo
- Gemini 4 Argon1,517.17Independent
Google DeepMind
- Claude Opus 5.51,508.73Independent
Anthropic
- Claude Fable 5.11,503.19Independent
Anthropic
- Gemini 3.8 Flash1,495.7Independent
Google DeepMind
- GPT-6.1 Sol1,479.94Independent
OpenAI
- GPT-6 Astra1,476.48Independent
OpenAI
Score links open the source; hover for capture details. Bar lengths start at zero. Arena lengths use the full public board maximum.
The shape of the scores
First three featured models. Toggle a name to isolate a line. Missing readings leave gaps, not zeroes.
3 of 3 series shown.
Axes share drawing space, not meaning. Arena is Elo divided by the current board maximum; it is not a percentage accuracy.
The newest arrival
Released 2026-10-21 · At least two readings
No predecessor is linked in the catalog yet. We do not infer a generation jump from a name.
Latest release with linked lineage
Claude Fable 5.1 vs Claude Fable 5
Latest snapshots, not a controlled before-and-after trial. Capture dates and evaluation setups may differ.
Scores and sources
| Model | Metric | Score / provenance | Captured | Source label / votes |
|---|---|---|---|---|
| Claude Opus 5.5 | CodingBenchLM.ai | 82.82Independent | 2026-11-08 | Claude Opus 5.5 |
| Claude Fable 5.1 | CodingBenchLM.ai | 76.58Independent | 2026-11-08 | Claude Fable 5.1 |
| GPT-6 Astra | CodingBenchLM.ai | 74.83Independent | 2026-11-08 | GPT-6 Astra |
| Gemini 4 Argon | CodingBenchLM.ai | 72.24Independent | 2026-11-08 | Gemini 4 Argon |
| GPT-6.1 Sol | CodingBenchLM.ai | 70.39Independent | 2026-11-08 | GPT-6.1 Sol |
| Gemini 3.8 Flash | CodingBenchLM.ai | 60.02Independent | 2026-11-08 | Gemini 3.8 Flash |
| Claude Opus 5.5 | AgenticBenchLM.ai | 89.3Independent | 2026-11-08 | Claude Opus 5.5 |
| Claude Fable 5.1 | AgenticBenchLM.ai | 80.15Independent | 2026-11-08 | Claude Fable 5.1 |
| Gemini 4 Argon | AgenticBenchLM.ai | 77.66Independent | 2026-11-08 | Gemini 4 Argon |
| GPT-6.1 Sol | AgenticBenchLM.ai | 75.84Independent | 2026-11-08 | GPT-6.1 Sol |
| GPT-6 Astra | AgenticBenchLM.ai | 73.33Independent | 2026-11-08 | GPT-6 Astra |
| Gemini 3.8 Flash | AgenticBenchLM.ai | 64.26Independent | 2026-11-08 | Gemini 3.8 Flash |
| GPT-6 Astra | ReasoningBenchLM.ai | 91.6Independent | 2026-11-08 | GPT-6 Astra |
| GPT-6.1 Sol | ReasoningBenchLM.ai | 88.8Independent | 2026-11-08 | GPT-6.1 Sol |
| Gemini 4 Argon | ReasoningBenchLM.ai | 85.2Independent | 2026-11-08 | Gemini 4 Argon |
| Claude Opus 5.5 | ReasoningBenchLM.ai | 84.4Independent | 2026-11-08 | Claude Opus 5.5 |
| Claude Fable 5.1 | ReasoningBenchLM.ai | 83.5Independent | 2026-11-08 | Claude Fable 5.1 |
| Gemini 3.8 Flash | ReasoningBenchLM.ai | 72.6Independent | 2026-11-08 | Gemini 3.8 Flash |
| Claude Opus 5.5 | KnowledgeBenchLM.ai | 89.36Independent | 2026-11-08 | Claude Opus 5.5 |
| GPT-6.1 Sol | KnowledgeBenchLM.ai | 85.95Independent | 2026-11-08 | GPT-6.1 Sol |
| Claude Fable 5.1 | KnowledgeBenchLM.ai | 85.85Independent | 2026-11-08 | Claude Fable 5.1 |
| GPT-6 Astra | KnowledgeBenchLM.ai | 85.51Independent | 2026-11-08 | GPT-6 Astra |
| Gemini 4 Argon | KnowledgeBenchLM.ai | 80.55Independent | 2026-11-08 | Gemini 4 Argon |
| Gemini 3.8 Flash | KnowledgeBenchLM.ai | 69.8Independent | 2026-11-08 | Gemini 3.8 Flash |
| Gemini 4 Argon | ArenaLM Arena | 1,517.17Independent | 2026-10-26 | Gemini 4 Argon (High)10,083 votes |
| Claude Opus 5.5 | ArenaLM Arena | 1,508.73Independent | 2026-10-26 | Claude Opus 5.5 (High)10,322 votes |
| Claude Fable 5.1 | ArenaLM Arena | 1,503.19Independent | 2026-10-26 | Claude Fable 5.1 (Max)16,343 votes |
| Gemini 3.8 Flash | ArenaLM Arena | 1,495.7Independent | 2026-10-26 | Gemini 3.8 Flash (High)43,997 votes |
| GPT-6.1 Sol | ArenaLM Arena | 1,479.94Independent | 2026-10-26 | GPT-6.1 Sol (Max)8,305 votes |
| GPT-6 Astra | ArenaLM Arena | 1,476.48Independent | 2026-10-26 | GPT-6 Astra (Max)14,076 votes |
| Model | Metric / source | Score / provenance | Captured |
|---|---|---|---|
| Claude Opus 5.5 | MultimodalGroundedBenchLM.ai | 91.6Independent | 2026-11-08 |
| Claude Opus 5.5 | GDP.pdfEpoch AI | 30.6Independent | 2026-11-08 |
| Claude Fable 5.1 | Humanity's Last ExamEpoch AI | 46.5Independent | 2026-11-08 |
| Claude Fable 5.1 | GDP.pdfEpoch AI | 29.6Independent | 2026-11-08 |
| GPT-6 Astra | Humanity's Last ExamEpoch AI | 54.8Independent | 2026-11-08 |
| Gemini 4 Argon | GDP.pdfEpoch AI | 28.4Independent | 2026-11-08 |
| Gemini 3.8 Flash | MultimodalGroundedBenchLM.ai | 88Independent | 2026-11-08 |
| Gemini 3.8 Flash | Humanity's Last ExamEpoch AI | 44.5Independent | 2026-11-08 |
| Gemini 3.8 Flash | GDP.pdfEpoch AI | 23.4Independent | 2026-11-08 |
- Provider
- AnthropicOpenAIGoogle DeepMind
- Out yet?
- YesYesYes
- Status
- AvailableAvailableAvailable
- Release date
- Sep 22, 2026Jul 9, 2026Oct 14, 2026
- LM Arena?LM Arena's Elo-style rating from blind head-to-head votes: people compare two anonymous model answers and pick the better one. Higher is better.
- 1508.7Verify at LM ArenaOct 26, 20261485.1Verify at LM ArenaOct 26, 20261517.2Verify at LM ArenaOct 26, 2026
- Agentic?BenchLM.ai's score for multi-step agentic work - planning, tool use, and acting autonomously, normalized 0–100 across multiple benchmarks. Higher is better.
- 89.3Verify at BenchLM.aiNov 8, 202667.65Verify at BenchLM.aiNov 8, 202677.66Verify at BenchLM.aiNov 8, 2026
- Coding?BenchLM.ai's score for code generation and software-engineering tasks, normalized 0–100 across multiple benchmarks. Higher is better.
- 82.82Verify at BenchLM.aiNov 8, 202667.27Verify at BenchLM.aiNov 8, 202672.24Verify at BenchLM.aiNov 8, 2026
- InstructionFollowing?BenchLM.ai's score for following precise, detailed instructions, normalized 0–100 across multiple benchmarks. Higher is better.
- -89.1Verify at BenchLM.aiNov 8, 2026-
- Knowledge?BenchLM.ai's score for factual knowledge and question answering, normalized 0–100 across multiple benchmarks. Higher is better.
- 89.36Verify at BenchLM.aiNov 8, 202676.34Verify at BenchLM.aiNov 8, 202680.55Verify at BenchLM.aiNov 8, 2026
- MultimodalGrounded?BenchLM.ai's score for understanding grounded in images and documents, normalized 0–100 across multiple benchmarks. Higher is better.
- 91.6Verify at BenchLM.aiNov 8, 202689.7Verify at BenchLM.aiNov 8, 2026-
- Reasoning?BenchLM.ai's score for logic and multi-step reasoning problems, normalized 0–100 across multiple benchmarks. Higher is better.
- 84.4Verify at BenchLM.aiNov 8, 202674.5Verify at BenchLM.aiNov 8, 202685.2Verify at BenchLM.aiNov 8, 2026
- GDP.pdf?Epoch AI's GDP.pdf benchmark: extracting and analyzing information from real-world PDF documents. Higher is better.Epoch AI
- 30.6Verify at Epoch AINov 8, 202630.7Verify at Epoch AINov 8, 202628.4Verify at Epoch AINov 8, 2026
- HealthBench?OpenAI's HealthBench evaluation of healthcare conversation quality. This value is vendor-reported; higher is better.openai-system-card
- -57Verify at openai-system-cardJul 10, 2026-
- HealthBench Consensus?OpenAI's HealthBench Consensus evaluation. This value is vendor-reported; higher is better.openai-system-card
- -95.5Verify at openai-system-cardJul 10, 2026-
- HealthBench Hard?The harder subset of OpenAI's HealthBench healthcare evaluation. This value is vendor-reported; higher is better.openai-system-card
- -33.1Verify at openai-system-cardJul 10, 2026-
- HealthBench Professional?OpenAI's HealthBench Professional evaluation of model responses to realistic healthcare conversations. This value is vendor-reported; higher is better.openai-system-card
- -60.5Verify at openai-system-cardJul 10, 2026-
- Vibe rating?OutYet's community rating: signed-in users score the model 1–10. Shown as the average and the number of votes.
- -7.0 / 10 · 1-
- Predecessor
- ---
- Successor
- ---
| Open page → | Open page → | Open page → | |
|---|---|---|---|
| Provider | Anthropic | OpenAI | Google DeepMind |
| Out yet? | Yes | Yes | Yes |
| Status | Available | Available | Available |
| Release date | Sep 22, 2026 | Jul 9, 2026 | Oct 14, 2026 |
| LM Arena?LM Arena's Elo-style rating from blind head-to-head votes: people compare two anonymous model answers and pick the better one. Higher is better. | 1508.7Verify at LM ArenaOct 26, 2026 | 1485.1Verify at LM ArenaOct 26, 2026 | 1517.2Verify at LM ArenaOct 26, 2026 |
| Agentic?BenchLM.ai's score for multi-step agentic work - planning, tool use, and acting autonomously, normalized 0–100 across multiple benchmarks. Higher is better. | 89.3Verify at BenchLM.aiNov 8, 2026 | 67.65Verify at BenchLM.aiNov 8, 2026 | 77.66Verify at BenchLM.aiNov 8, 2026 |
| Coding?BenchLM.ai's score for code generation and software-engineering tasks, normalized 0–100 across multiple benchmarks. Higher is better. | 82.82Verify at BenchLM.aiNov 8, 2026 | 67.27Verify at BenchLM.aiNov 8, 2026 | 72.24Verify at BenchLM.aiNov 8, 2026 |
| InstructionFollowing?BenchLM.ai's score for following precise, detailed instructions, normalized 0–100 across multiple benchmarks. Higher is better. | - | 89.1Verify at BenchLM.aiNov 8, 2026 | - |
| Knowledge?BenchLM.ai's score for factual knowledge and question answering, normalized 0–100 across multiple benchmarks. Higher is better. | 89.36Verify at BenchLM.aiNov 8, 2026 | 76.34Verify at BenchLM.aiNov 8, 2026 | 80.55Verify at BenchLM.aiNov 8, 2026 |
| MultimodalGrounded?BenchLM.ai's score for understanding grounded in images and documents, normalized 0–100 across multiple benchmarks. Higher is better. | 91.6Verify at BenchLM.aiNov 8, 2026 | 89.7Verify at BenchLM.aiNov 8, 2026 | - |
| Reasoning?BenchLM.ai's score for logic and multi-step reasoning problems, normalized 0–100 across multiple benchmarks. Higher is better. | 84.4Verify at BenchLM.aiNov 8, 2026 | 74.5Verify at BenchLM.aiNov 8, 2026 | 85.2Verify at BenchLM.aiNov 8, 2026 |
| GDP.pdf?Epoch AI's GDP.pdf benchmark: extracting and analyzing information from real-world PDF documents. Higher is better.Epoch AI | 30.6Verify at Epoch AINov 8, 2026 | 30.7Verify at Epoch AINov 8, 2026 | 28.4Verify at Epoch AINov 8, 2026 |
| HealthBench?OpenAI's HealthBench evaluation of healthcare conversation quality. This value is vendor-reported; higher is better.openai-system-card | - | 57Verify at openai-system-cardJul 10, 2026 | - |
| HealthBench Consensus?OpenAI's HealthBench Consensus evaluation. This value is vendor-reported; higher is better.openai-system-card | - | 95.5Verify at openai-system-cardJul 10, 2026 | - |
| HealthBench Hard?The harder subset of OpenAI's HealthBench healthcare evaluation. This value is vendor-reported; higher is better.openai-system-card | - | 33.1Verify at openai-system-cardJul 10, 2026 | - |
| HealthBench Professional?OpenAI's HealthBench Professional evaluation of model responses to realistic healthcare conversations. This value is vendor-reported; higher is better.openai-system-card | - | 60.5Verify at openai-system-cardJul 10, 2026 | - |
| Vibe rating?OutYet's community rating: signed-in users score the model 1–10. Shown as the average and the number of votes. | - | 7.0 / 10 · 1 | - |
| Predecessor | - | - | - |
| Successor | - | - | - |
Benchmark scores are mirrored from third-party sources and captured on the dates shown. Numbers from different benchmarks, sources, or capture dates are not directly comparable.
Data from BenchLM.ai · Epoch AI, “AI Benchmarking Hub” (CC BY 4.0).