BlogLLM Benchmark Scores as Published, Side by Side
Claude Fable 5.2: Benchmark Scores as Published
Every result the catalog holds for Claude Fable 5.2: 46 tests in 10 areas, from 5 pages. 41 printed by Anthropic itself, the rest by the company named beside each number. Each number is as printed; nothing is ranked or rescored.
Developer AnthropicReleased 2026-11-09Context window 1MMax output 128KInput Text, imageOutput TextWeights ClosedData version 2026111201, as of 2026-11-12
Knowledge Work
Agentic Coding
Science and Math
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPQA Diamond | 93.9% | Epoch AI, Epoch AI Benchmarking Hubchecked 2026-11-10 | Effort: max |
| Terminal-Bench Science 0.1 | 74.6% | Anthropic, Claude Fable 5.2 and Mythos 5.2checked 2026-11-09; printed on 1 more page | - |
| FrontierMath Tier 4 (v2) | 100% | Epoch AI, Epoch AI Benchmarking Hubchecked 2026-11-10 | Effort: max |
| FrontierMath Tier 1-3 (v2) | 95.1% | Epoch AI, Epoch AI Benchmarking Hubchecked 2026-11-10 | Effort: max |
Computer Use
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| OSWorld 2.1 offline subset | 89.3% | Anthropic, Claude Fable 5.2 and Mythos 5.2checked 2026-11-09; printed on 1 more page | - |
| OSWorld 2.1 binary | 54.6% | Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2checked 2026-11-09 | - |
Multimodal Understanding
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Chartography (no tools) | 73.4% | Anthropic, Claude Fable 5.2 and Mythos 5.2checked 2026-11-09; printed on 1 more page | - |
| Chartography (with tools) | 91.6% | Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2checked 2026-11-09 | Effort: max |
General Knowledge and Reasoning
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Humanity's Last Exam (no tools) | 73.2% | Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2checked 2026-11-09 | Effort: max |
| Humanity's Last Exam (with tools) | 74.2% | Anthropic, Claude Fable 5.2 and Mythos 5.2checked 2026-11-09; printed on 1 more page | - |
| SimpleQA Verified | 94% | Epoch AI, Epoch AI Benchmarking Hubchecked 2026-11-10 | Effort: max |
| ARC-AGI-3 | 79.26% | Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2checked 2026-11-09 | Effort: high; Harness: Standard |
| 65.66% | Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2checked 2026-11-09 | Effort: max; Harness: Standard | |
| ARC-AGI-3 (Provider Adapter harness) | 97.72% | Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2checked 2026-11-09 | Effort: high; Harness: Provider Adapter |
| 94.9% | Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2checked 2026-11-09 | Effort: max; Harness: Provider Adapter |
Web Search and Research
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| WANDR (relaxed score) | 82.1% | Anthropic, Claude Fable 5.2 and Mythos 5.2checked 2026-11-09; printed on 1 more page | - |
Multilingual
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Global-MMLU | 96% | Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2checked 2026-11-09 | Effort: max |
| MILU | 94.1% | Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2checked 2026-11-09 | Effort: max |
Healthcare
Engineering and Design
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| RoboDojo Sim | 64.9% | Anthropic, Claude Fable 5.2 and Mythos 5.2checked 2026-11-09 | - |
| BenchCAD 2.1 Core (no tools) | 75.4% | Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2checked 2026-11-09 | Dataset revision: v2.1 |
| BenchCAD 2.1 Core (with tools) | 83.5% | Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2checked 2026-11-09 | Dataset revision: v2.1 |
Price
API list prices in US dollars per one million tokens, as printed on the developer's pricing page on the day checked. Cost per task is measured by Vals AI.
| Price | Value | Printed by | Setup as printed |
|---|---|---|---|
| Input | $8 | Anthropic, Anthropic API pricingchecked 2026-11-09 | - |
| Cached input | $0.2 | Anthropic, Anthropic API pricingchecked 2026-11-09 | - |
| Cache write | $10 | Anthropic, Anthropic API pricingchecked 2026-11-09 | Cache: 5 minute cache |
| Cache write, 1 hour | $16 | Anthropic, Anthropic API pricingchecked 2026-11-09 | - |
| Output | $40 | Anthropic, Anthropic API pricingchecked 2026-11-09 | - |
| Input, batch | $4 | Anthropic, Anthropic API pricingchecked 2026-11-09 | - |
| Output, batch | $20 | Anthropic, Anthropic API pricingchecked 2026-11-09 | - |
| Input, fast | $16 | Anthropic, Anthropic API pricingchecked 2026-11-09 | - |
| Output, fast | $80 | Anthropic, Anthropic API pricingchecked 2026-11-09 | - |
| Cost per taskVals AI, USD, lower is better | $22.13 | Vals AI, Vibe Code Bench v1.1 leaderboardchecked 2026-11-09 | Harness: OpenHands |
Side by side
More from Anthropic
- Claude Mythos 5.2
- Claude Haiku 5.5
- Claude Sonnet 5.5
- Claude Opus 5.5
- Claude Fable 5.1
- Claude Mythos 5.1
- Claude Opus 5
- Claude Sonnet 5
- Claude Fable 5
- Claude Mythos 5
- Claude Opus 4.8
- Claude Opus 4.7
- Claude Mythos Preview
- Claude Sonnet 4.6
- Claude Opus 4.6
- Claude Opus 4.5
- Claude Haiku 4.5
- Claude Sonnet 4.5
- Claude Opus 4.1
- Claude Opus 4
- Claude Sonnet 4
- Claude 3.7 Sonnet
- Claude 3.5 Sonnet
Every number here is read from the same catalog file as the benchmark table, data version 2026111201. Where one page printed the model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.