Meta AINew
Muse Ember
- Released Nov. 9, 2026
- $0.10 in / $0.50 out per million tokens
- Reads up to 1M tokens at once
No independent scores yet. Testers usually publish within days of a release.
AI Scoreboard
When a lab ships a new model, this is how it measures up: independent test scores, price and release date, next to the models it competes with.
Just released
GoogleNew
Gemini Omni 1.2 Flash
- Released Nov. 5, 2026
- $1.50 in / $9 out per million tokens
- Reads up to 131K tokens at once
No independent scores yet. Testers usually publish within days of a release.
GoogleNew
Gemini Omni 1.1 Flash
- Released Nov. 4, 2026
- $1.50 in / $9 out per million tokens
- Reads up to 131K tokens at once
No independent scores yet. Testers usually publish within days of a release.
TencentNew
Hy4
- Released Nov. 4, 2026
- $0.42 in / $1.25 out per million tokens
- Reads up to 1M tokens at once
No independent scores yet. Testers usually publish within days of a release.
AnthropicNew
Claude Fable 5.2
- Released Nov. 9, 2026
- Paid API
- $8 in / $40 out per million tokens
- Reads up to 1M tokens at once
Not enough tests yet for an overall score. The results so far:
| Test | Claude Fable 5.2 | GPT-6 AstraOpenAI | Gemini 4 ArgonGoogle DeepMind | Muse WonderMeta AI | Claude Opus 5.5Same lab, earlier |
|---|---|---|---|---|---|
| OverallEpoch Capabilities Index | —Not tested yet | 169.1 (best here) | 166.5 | 162.0 | 168.4 |
| ScienceGPQA Diamond | 93.9% | 95.8% | 96.4% (best here) | —Not tested yet | 90.6% |
| MathFrontierMath, Tiers 1–3 | 95.1% (best here) | 93.7% | 86% | 82.1% | 91.2% |
| PuzzlesARC-AGI-2 | 93.8% | 95% (best here) | 91.3% | —Not tested yet | 93.3% |
| FactsSimpleQA Verified | 94% (best here) | 75.6% | 76% | —Not tested yet | 72.2% |
| Priceper million tokens | $8 in / $40 out | $10 in / $50 out | $2 in / $10 out | $4 in / $20 out | $4 in / $20 out |
No published result yet for Claude Fable 5.2 on: Coding, Science code, Office work, Physics.
Thinking MachinesNew
Inkling 2 Small
- Released Nov. 5, 2026
Not enough tests yet for an overall score. The results so far:
| Test | Inkling 2 Small | GPT-6 AstraOpenAI | Claude Opus 5.5Anthropic | Gemini 4 ArgonGoogle DeepMind |
|---|---|---|---|---|
| OverallEpoch Capabilities Index | —Not tested yet | 169.1 (best here) | 168.4 | 166.5 |
| PuzzlesARC-AGI-2 | 81.7% | 95% (best here) | 93.3% | 91.3% |
| Science codeSciCode | 52.3% | 56.5% | 66.9% (best here) | 61.8% |
| Office workAPEX-Agents | 46.8% | 64.7% | 73.5% | 82.4% (best here) |
| Priceper million tokens | — | $10 in / $50 out | $4 in / $20 out | $2 in / $10 out |
No published result yet for Inkling 2 Small on: Science, Math, Coding, Facts, Physics.
ByteDance
Doubao Seed Evolving (Nov 2026)
- Released Nov. 2, 2026
- Paid API
Not enough tests yet for an overall score. The results so far:
| Test | Doubao Seed Evolving (Nov 2026) | GPT-6 AstraOpenAI | Claude Opus 5.5Anthropic | Gemini 4 ArgonGoogle DeepMind |
|---|---|---|---|---|
| OverallEpoch Capabilities Index | —Not tested yet | 169.1 (best here) | 168.4 | 166.5 |
| ScienceGPQA Diamond | 93.1% | 95.8% | 90.6% | 96.4% (best here) |
| FactsSimpleQA Verified | 41.9% | 75.6% | 72.2% | 76% (best here) |
| Priceper million tokens | — | $10 in / $50 out | $4 in / $20 out | $2 in / $10 out |
No published result yet for Doubao Seed Evolving (Nov 2026) on: Math, Puzzles, Coding, Science code, Office work, Physics.
Also new: Mistral Large 4 (Mistral AI, Oct. 29) · GPT-6.1 Terra (OpenAI, Oct. 26) · Kimi K3.1 Pro (Moonshot, Oct. 23) · DeepSeek V4.1 Flash 1017 (DeepSeek, Oct. 17) · Muse Spark Open (Meta AI, Oct. 15)
Every model, test by test
| Model | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| GPT-6 AstraOpenAI | 169.1 | 95.8% | 93.7% | 95% | 53.3% | 56.5% | 64.7% | 75.6% | 31.7% | $10 / $50 | Sept. 3 |
| GPT-6.1 SolOpenAI | 168.9 | 95.4% | 93.7% | 94.2% | 50.2% | 55.8% | 60% | 73.9% | 31.7% | $2 / $10 | Sept. 29 |
| Claude Opus 5.5Anthropic | 168.4 | 90.6% | 91.2% | 93.3% | 54.6% | 66.9% | 73.5% | 72.2% | 31.7% | $4 / $20 | Sept. 22 |
| GPT-6.1 TerraOpenAI | 167.8 | 94.3% | 90.9% | — | — | 55.1% | 68.3% | 57.3% | 28% | $1 / $5 | Oct. 26 |
| Claude Fable 5.1Anthropic | 166.9 | — | 90.2% | 90% | 50.9% | 63.1% | 68.6% | 70.8% | 31.1% | $10 / $50 | Sept. 1 |
| Gemini 4 ArgonGoogle DeepMind | 166.5 | 96.4% | 86% | 91.3% | 47.6% | 61.8% | 82.4% | 76% | 27.1% | $2 / $10 | Sept. 30 |
| Claude Sonnet 5.5Anthropic | 166.2 | 95.6% | 88.8% | 83.9% | 52.1% | 61% | 75.5% | 46.5% | 31.4% | $2 / $10 | Sept. 28 |
| Claude Opus 5Anthropic | 164.5 | 93.9% | 85.6% | 90.4% | 53.4% | 56.4% | 65.8% | 59.9% | 29.1% | $5 / $25 | July 24 |
| Claude Fable 5Anthropic | 164.2 | 85.9% | 87% | 89.2% | 53.5% | 61% | 63.6% | 70.7% | 28.6% | $10 / $50 | June 9 |
| GPT-6 SolOpenAI | 164.1 | 94.3% | 89.8% | 89.6% | 49.3% | 57.6% | 54.3% | 60.7% | 30.9% | $2 / $10 | Sept. 22 |
| GPT-5.6 SolOpenAI | 163.0 | 93.5% | 89.1% | 92.5% | 47.5% | 57.8% | 51.4% | 69.7% | 32.3% | $4 / $20 | July 9 |
| GPT-5.5 ProOpenAI | 162.7 | 93.9% | 87.7% | 84.6% | — | — | — | — | 30.6% | $30 / $180 | April 23 |
| Muse WonderMeta AI | 162.0 | — | 82.1% | — | — | 60.3% | 66.1% | — | 28.3% | $4 / $20 | Oct. 12 |
| GPT-5.6 TerraOpenAI | 160.9 | 93.3% | 86% | 83.9% | 41.3% | 55% | 58.2% | 43.2% | 30% | $2 / $12 | July 9 |
| Claude Haiku 5.5Anthropic | 160.2 | 89.6% | 75.1% | 61.3% | 46.4% | 55% | 56.1% | 23.8% | 22.6% | $0.10 / $0.50 | Oct. 7 |
| GPT-5.4 ProOpenAI | 160.2 | 94.6% | 82.5% | 83.3% | — | — | — | 46.3% | 30% | $30 / $180 | March 5 |
| GPT-5.5OpenAI | 160.0 | 94% | 85.3% | 85% | 43% | 56.1% | 55.1% | 63% | 27.1% | $5 / $30 | April 23 |
| Claude Opus 4.8Anthropic | 159.9 | 91% | 80% | 72.1% | 46.5% | 53.5% | 48.9% | 53% | 20.9% | $5 / $25 | May 28 |
| DeepSeek V4.1 Flash 1017DeepSeek · open weights | 159.3 | 93.2% | 71.2% | 78.1% | — | 55.9% | 69.8% | 42.5% | 24% | $0.01 / $0.50 | Oct. 17 |
| Gemini 3.8 FlashGoogle DeepMind | 158.6 | 95.4% | 68.4% | 89.2% | 41.2% | 56.6% | 64.3% | 69.7% | 18.3% | $0.83 / $4.13 | Sept. 2 |
| Kimi K3Moonshot · open weights | 158.5 | 93.1% | 72.2% | 60.4% | 44.2% | 59.5% | 47.8% | 50.6% | 23.4% | $0.19 / $16 | July 16 |
| Gemini 3.7 FlashGoogle DeepMind | 158.4 | 94.8% | 71.6% | 84.6% | 43.6% | 59.8% | 67.8% | 69.2% | 14.3% | $0.75 / $3.75 | Aug. 13 |
| Muse Spark 1.3Meta AI | 158.0 | — | 74.4% | — | — | 59.7% | 58.6% | — | 26% | $1.25 / $4.25 | Sept. 2 |
| Grok 4.6xAI | 157.9 | 94% | 66% | 67.1% | 48% | 56.5% | 65.3% | 49.3% | 19.7% | $2 / $6 | Aug. 12 |
| GPT-5.4OpenAI | 157.8 | 93.3% | 78.6% | 74% | — | 56.6% | 52.4% | 45.1% | 23.4% | $2.50 / $15 | March 5 |
| Claude Opus 4.7Anthropic | 157.6 | 90.2% | 70.2% | 75.8% | 38.5% | 54.5% | 49.2% | 51.7% | 12% | $5 / $25 | April 16 |
| Qwen 3.8 MaxAlibaba | 157.4 | 92.7% | 74.7% | — | — | 53.2% | 63.3% | 45.8% | 20% | — | Aug. 2 |
| GPT-5.2 ProOpenAI | 157.2 | — | 74% | 54.2% | — | — | — | — | — | $21 / $168 | Dec. 11 |
| GLM-5.3Z.ai (Zhipu AI) · open weights | 156.9 | 90.9% | 68.8% | — | 40.1% | 59% | 56.6% | 41% | 19.1% | $0.07 / $1.40 | Aug. 14 |
| GPT-5.6 LunaOpenAI | 156.8 | 91.6% | 82.1% | 59.5% | 39.8% | 53.6% | 43% | 41% | 20.6% | $0.20 / $1.20 | July 9 |
| GPT-6 LunaOpenAI | 156.7 | 90.5% | 78.9% | 59.3% | 42.4% | 54.6% | 44.3% | 41.4% | 19.4% | $0.10 / $0.50 | Sept. 22 |
| Claude Sonnet 5Anthropic | 156.7 | 90.5% | 65.6% | — | 42.7% | 54.3% | 54.5% | 33.7% | 16.9% | $2 / $10 | June 30 |
| DeepSeek V4.1 FlashDeepSeek · open weights | 156.5 | 89.8% | 67.4% | 72.9% | 43.9% | 51.9% | 39.5% | 42.9% | 14.3% | $0.05 / $0.57 | Sept. 9 |
| Claude Opus 4.6Anthropic | 156.3 | 90.5% | 66% | 69.2% | 26.6% | — | 46.3% | 47% | — | $5 / $25 | Feb. 5 |
| Gemini 3.1 ProGoogle DeepMind | 156.2 | 94.4% | 59.6% | 77.1% | — | 58.7% | 35.1% | 73.5% | 17.7% | — | Feb. 19 |
| Grok 4.7xAI | 156.1 | 92.7% | 53% | 61.4% | 47.6% | 57.8% | 54.6% | 56% | 18% | $2 / $6 | Sept. 21 |
| Qwen3.8 Max (0902)Alibaba | 155.9 | 92.3% | 65.6% | — | — | 52.1% | — | 47.3% | 17.7% | $2 / $6 | Sept. 1 |
| DeepSeek V4 Pro 0813DeepSeek · open weights | 155.9 | 91.7% | 64.6% | 61.3% | 28.6% | 51% | 47.3% | 52.9% | 18% | $0.11 / $4.44 | Aug. 13 |
| Muse Spark OpenMeta AI · open weights | 155.4 | 88.6% | 69.8% | 57.5% | — | 58.4% | 33.4% | 56.6% | 14.9% | $1.25 / $4.25 | Oct. 15 |
| Gemini 3.6 FlashGoogle DeepMind | 155.2 | 94.1% | 58.9% | 60.4% | 34.4% | 53.4% | 46.9% | 66.2% | 10.6% | $0.75 / $3.75 | July 21 |
| Mistral Large 4Mistral AI · open weights | 154.7 | 90.2% | — | — | — | — | — | 22.4% | 11.1% | $0.70 / $2.10 | Oct. 29 |
| Mistral Large 4 PreviewMistral AI · open weights | 152.6 | 88.1% | 58.6% | — | 39.4% | 54.2% | 51.6% | 20% | 10.6% | — | Oct. 6 |
| Beam 1.0Reflection · open weights | 150.8 | — | — | 23.5% | — | 48.5% | 48.8% | — | 13.1% | — | Oct. 5 |
| Claude Fable 5.2NewAnthropic | — | 93.9% | 95.1% | 93.8% | — | — | — | 94% | — | $8 / $40 | Nov. 9 |
| Doubao Seed Evolving (Nov 2026)ByteDance | — | 93.1% | — | — | — | — | — | 41.9% | — | — | Nov. 2 |
| Gemini 4 CarbonGoogle DeepMind | — | — | — | — | — | 64.2% | 84.2% | — | 36% | — | Oct. 28 |
| Gemini Omni 1.1 FlashNewGoogle | — | — | — | — | — | — | — | — | — | $1.50 / $9 | Nov. 4 |
| Gemini Omni 1.2 FlashNewGoogle | — | — | — | — | — | — | — | — | — | $1.50 / $9 | Nov. 5 |
| Hy4NewTencent | — | — | — | — | — | — | — | — | — | $0.42 / $1.25 | Nov. 4 |
| Inkling 2 SmallNewThinking Machines | — | — | — | 81.7% | — | 52.3% | 46.8% | — | — | — | Nov. 5 |
| Kimi K3.1 ProMoonshot · open weights | — | 94.2% | 78.2% | — | — | 60.8% | 65.5% | 62.2% | 24.6% | $2 / $10 | Oct. 23 |
| Muse EmberNewMeta AI | — | — | — | — | — | — | — | — | — | $0.10 / $0.50 | Nov. 9 |
What the tests measure
- Overall Epoch Capabilities Index · Epoch AI
- One overall score. Epoch AI combines a model’s results on dozens of tests into a single number, so models that took different tests can still be compared. Higher is better; a few points apart is within the margin of error.
- Science GPQA Diamond · run by Epoch AI
- Graduate-level multiple-choice questions in physics, chemistry and biology. Guessing scores 25%.
- Math FrontierMath, Tiers 1–3 · run by Epoch AI
- Original math problems, from hard undergraduate level to early research level, kept private so a model cannot have seen the answers.
- Puzzles ARC-AGI-2 · ARC Prize Foundation
- Visual pattern puzzles that most people can solve. Each one needs working out a new rule, not recalling facts.
- Coding FrontierCode · Cognition
- Hard programming tasks an AI agent has to finish on its own.
- Science code SciCode · Artificial Analysis
- Writing code to solve problems taken from real scientific research.
- Office work APEX-Agents · Mercor
- Long professional tasks of the kind done in banking, consulting and law, with one attempt each.
- Facts SimpleQA Verified · run by Epoch AI
- Short factual questions with one right answer, answered without looking anything up.
- Physics CritPt · CritPt
- Unpublished research-level physics problems.
A test score is not the whole model. Labs tune for well-known tests, small gaps are often noise, and none of these measures whether a model is right for a given job. A dash means nobody has published that test for that model yet.
Scores: Epoch AI Benchmarking Hub (CC BY 4.0), each the model’s best result across the settings tested, as of Nov. 9, 2026. Release dates and prices: OpenRouter. The paper runs none of these tests.