Nova Premier 1.0 vs Claude Fable 5.1
Claude Fable 5.1 leads Nova Premier 1.0 on the Artificial Analysis Intelligence Index, 53.4 to 9.2, and Nova Premier 1.0 costs 4.0x less per output token ($12.50 vs $50.00 per million). Updated October 21, 2026; 6 benchmarks have a result for both.
vs boards won of 6 shared
Nova Premier 1.0 or Claude Fable 5.1: which to pick
Only Claude Fable 5.1 has a coding score, 84.2 on the Vibe Coding Index; Nova Premier 1.0 has none, so the two cannot be ranked on coding.
Pick Nova Premier 1.0 for output tokens 4.0x cheaper ($12.50 vs $50.00 per million).
Model ANova Premier 1.0AmazonNot benchmarkedNo coding benchmarkNo cost per solved taskModel BClaude Fable 5.1Anthropic84.2/1005 independent benchmarksNo cost per solved task
- Shared results
- 6
- Nova Premier 1.0 only
- 8
- Claude Fable 5.1 only
- 118
- Like-for-like categories
- 5 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Only Claude Fable 5.1 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
Claude Fable 5.1
Claude Fable 5.1 leads, 53.4 against 9.2.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Claude Fable 5.1 has a AA Agentic Index result, 57.9.
Directional only
Reasoning
GPQA Diamond
No call
Only Claude Fable 5.1 has a GPQA Diamond result, 93.4%.
Directional only
Knowledge
MMLU Pro
No call
Only Claude Fable 5.1 has a MMLU Pro result, 92.4%.
Directional only
Web design
Design Arena: websites
Claude Fable 5.1
Claude Fable 5.1 leads, 1313 against 835.
Same board, both measured
Long documents
Listed context window
No call
Both take 1M tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Nova Premier 1.0
Nova Premier 1.0 $0.0088, Claude Fable 5.1 $0.035 per turn.
List prices
At a glance
- Coding index
- Nova Premier 1.0 not benchmarked, Claude Fable 5.1 84.2 from 5 benchmarks.
- Widest category
- Coding, 66.5 points apart on average over 1 shared benchmark.
- Widest single gap
- ALE-Bench: Nova Premier 1.0 147.4 against Claude Fable 5.1 2143.2, 66.5 points apart on a 0 to 100 scale.
- Output price
- Nova Premier 1.0 $12.50 against Claude Fable 5.1 $50.00 per million output tokens, 4.0x apart.
- Context window
- Both take 1M tokens.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Nova Premier 1.0 | Bars | Claude Fable 5.1 | Ties |
|---|---|---|---|---|
| Coding | 0 | 1 | ||
| Intelligence | 0 | 1 | ||
| Reasoning | 0 | 2 | ||
| Web design | 0 | 1 | ||
| General | 0 | 1 | ||
| All shared boards | 0 | 6 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index01
| Benchmark | Nova Premier 1.0 | Claude Fable 5.1 | Leader |
|---|---|---|---|
| LiveBench coding | Not measured | 97.7% | Only Claude Fable 5.1 measured |
| LMArena WebDev | Not measured | 1743 | Only Claude Fable 5.1 measured |
| AA Coding Index | Not measured | 81.6 | Only Claude Fable 5.1 measured |
| LiveCodeBench (Vals AI) | Not measured | 90.5% | Only Claude Fable 5.1 measured |
| Terminal-Bench 4 (Vals AI) | Not measured | 58.1% | Only Claude Fable 5.1 measured |
| Vibe Code Bench (Vals AI) | Not measured | 90.3% | Only Claude Fable 5.1 measured |
| Code migration (Vals AI) | Not measured | 54.6% | Only Claude Fable 5.1 measured |
| ProgramBench (Vals AI) | Not measured | 7.0% | Only Claude Fable 5.1 measured |
| IOI (Vals AI) | Not measured | 90.8% | Only Claude Fable 5.1 measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 85.0% | Only Claude Fable 5.1 measured |
| SWE-bench Multimodal (Vals AI) | Not measured | 61.3% | Only Claude Fable 5.1 measured |
| Vibe Code Bench 1-100 (Vals AI) | Not measured | 28.0% | Only Claude Fable 5.1 measured |
| SkillsBench (Vals AI) | Not measured | 61.5% | Only Claude Fable 5.1 measured |
| CyberBench (Vals AI) | Not measured | 70.4% | Only Claude Fable 5.1 measured |
| LiveCodeBench (Artificial Analysis run) | 31.7% | Not measured | Only Nova Premier 1.0 measured |
| SciCode | Not measured | 63.1% | Only Claude Fable 5.1 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 6.8% | Not measured | Only Nova Premier 1.0 measured |
| FrontierCode | Not measured | 50.9% | Only Claude Fable 5.1 measured |
| FrontierSWE | Not measured | 56.3% | Only Claude Fable 5.1 measured |
| GSO-Bench | Not measured | 88.2% | Only Claude Fable 5.1 measured |
| WeirdML | Not measured | 92.9% | Only Claude Fable 5.1 measured |
| MirrorCode | Not measured | 73.3% | Only Claude Fable 5.1 measured |
| ALE-Bench | 147.4 | 2143.2 | Claude Fable 5.1 |
| LMArena Text: coding | Not measured | 1532 | Only Claude Fable 5.1 measured |
| LMArena Text: software and IT | Not measured | 1530 | Only Claude Fable 5.1 measured |
| LMArena WebDev: React | Not measured | 1792 | Only Claude Fable 5.1 measured |
| LMArena WebDev: HTML | Not measured | 1684 | Only Claude Fable 5.1 measured |
| LMArena WebDev: from an image | Not measured | 1722 | Only Claude Fable 5.1 measured |
| Neither model has a result on the other 11 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Nova Premier 1.0 | Claude Fable 5.1 | Leader |
|---|---|---|---|
| AA Intelligence Index | 9.2 | 53.4 | Claude Fable 5.1 |
| Epoch Capabilities Index | Not measured | 166.5 | Only Claude Fable 5.1 measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index25 boards, none shared
| Benchmark | Nova Premier 1.0 | Claude Fable 5.1 | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 57.9 | Only Claude Fable 5.1 measured |
| Design Arena: agents building web apps | Not measured | 1318 | Only Claude Fable 5.1 measured |
| Design Arena: agents building full-stack apps | Not measured | 1326 | Only Claude Fable 5.1 measured |
| Design Arena: agents building mobile apps | Not measured | 1267 | Only Claude Fable 5.1 measured |
| Design Arena: agents building Godot games | Not measured | 1327 | Only Claude Fable 5.1 measured |
| Design Arena: PowerPoint slides | Not measured | 1327 | Only Claude Fable 5.1 measured |
| Design Arena: spreadsheets | Not measured | 1365 | Only Claude Fable 5.1 measured |
| LiveBench research | Not measured | 82.0% | Only Claude Fable 5.1 measured |
| LiveBench browser | Not measured | 100.0% | Only Claude Fable 5.1 measured |
| LiveBench long agentic | Not measured | 80.8% | Only Claude Fable 5.1 measured |
| SREBench (Vals AI) | Not measured | 22.9% | Only Claude Fable 5.1 measured |
| Finance Agent (Vals AI) | Not measured | 58.9% | Only Claude Fable 5.1 measured |
| Tax Agent Bench (Vals AI) | Not measured | 49.2% | Only Claude Fable 5.1 measured |
| Legal Research Bench (Vals AI) | Not measured | 55.3% | Only Claude Fable 5.1 measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 76.7% | Only Claude Fable 5.1 measured |
| Terminal-Bench-Science (Vals AI) | Not measured | 40.0% | Only Claude Fable 5.1 measured |
| Time Horizon Index (Vals AI) | Not measured | 63.3% | Only Claude Fable 5.1 measured |
| CUA-bench (Vals AI) | Not measured | 13.2% | Only Claude Fable 5.1 measured |
| Robo-bench (Vals AI) | Not measured | 5.8% | Only Claude Fable 5.1 measured |
| τ²-Bench Telecom | 38.3% | Not measured | Only Nova Premier 1.0 measured |
| APEX-Agents | Not measured | 68.6% | Only Claude Fable 5.1 measured |
| Remote Labor Index | Not measured | 17.9% | Only Claude Fable 5.1 measured |
| SpireClimb | Not measured | 2.0% | Only Claude Fable 5.1 measured |
| Vending-Bench 2 | Not measured | $5,422 | Only Claude Fable 5.1 measured |
| LMArena Search | Not measured | 1246 | Only Claude Fable 5.1 measured |
| Neither model has a result on the other 16 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Nova Premier 1.0 | Claude Fable 5.1 | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 93.4% | Only Claude Fable 5.1 measured |
| LiveBench reasoning | Not measured | 91.7% | Only Claude Fable 5.1 measured |
| MysteryMechanism (Vals AI) | Not measured | 47.8% | Only Claude Fable 5.1 measured |
| MMMU Pro (Vals AI) | Not measured | 90.6% | Only Claude Fable 5.1 measured |
| GPQA Diamond (Artificial Analysis run) | 56.9% | 93.7% | Claude Fable 5.1 |
| Humanity's Last Exam (Artificial Analysis run) | 4.2% | 59.1% | Claude Fable 5.1 |
| ARC-AGI | Not measured | 97.5% | Only Claude Fable 5.1 measured |
| ARC-AGI-2 | Not measured | 90.0% | Only Claude Fable 5.1 measured |
| Chess puzzles | Not measured | 48.0% | Only Claude Fable 5.1 measured |
| Mystery game puzzles | Not measured | 58.0% | Only Claude Fable 5.1 measured |
| EBR-bench | Not measured | 57.1% | Only Claude Fable 5.1 measured |
| LMArena Text: hard prompts | Not measured | 1528 | Only Claude Fable 5.1 measured |
| LMArena Text: expert | Not measured | 1544 | Only Claude Fable 5.1 measured |
| LMArena Text: hard prompts in English | Not measured | 1522 | Only Claude Fable 5.1 measured |
| LMArena Vision: diagrams | Not measured | 1343 | Only Claude Fable 5.1 measured |
| LMArena Vision: homework | Not measured | 1345 | Only Claude Fable 5.1 measured |
| Kagi LLM Benchmark | 44.8% | Not measured | Only Nova Premier 1.0 measured |
| Neither model has a result on the other 5 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Nova Premier 1.0 | Claude Fable 5.1 | Leader |
|---|---|---|---|
| AA Math Index | 17.3 | Not measured | Only Nova Premier 1.0 measured |
| AIME 2025 (Artificial Analysis run) | 17.3% | Not measured | Only Nova Premier 1.0 measured |
| OTIS Mock AIME | Not measured | 100.0% | Only Claude Fable 5.1 measured |
| FrontierMath, tiers 1 to 3 | Not measured | 90.2% | Only Claude Fable 5.1 measured |
| FrontierMath, tier 4 | Not measured | 87.8% | Only Claude Fable 5.1 measured |
| ProofBench | Not measured | 100.0% | Only Claude Fable 5.1 measured |
| LMArena Text: math | Not measured | 1531 | Only Claude Fable 5.1 measured |
| LMArena Text: mathematical work | Not measured | 1541 | Only Claude Fable 5.1 measured |
| Neither model has a result on the other 5 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index11 boards, none shared
| Benchmark | Nova Premier 1.0 | Claude Fable 5.1 | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 92.4% | Only Claude Fable 5.1 measured |
| LegalBench (Vals AI) | Not measured | 88.5% | Only Claude Fable 5.1 measured |
| TaxEval (Vals AI) | Not measured | 76.0% | Only Claude Fable 5.1 measured |
| MortgageTax (Vals AI) | Not measured | 70.8% | Only Claude Fable 5.1 measured |
| MedCode (Vals AI) | Not measured | 53.5% | Only Claude Fable 5.1 measured |
| MMLU Pro (Artificial Analysis run) | 73.3% | Not measured | Only Nova Premier 1.0 measured |
| SimpleQA Verified | Not measured | 70.8% | Only Claude Fable 5.1 measured |
| LMArena Text: science | Not measured | 1532 | Only Claude Fable 5.1 measured |
| LMArena Text: medicine and healthcare | Not measured | 1531 | Only Claude Fable 5.1 measured |
| LMArena Text: legal and government | Not measured | 1514 | Only Claude Fable 5.1 measured |
| LMArena Text: business and finance | Not measured | 1493 | Only Claude Fable 5.1 measured |
| Neither model has a result on the other 7 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Nova Premier 1.0 | Claude Fable 5.1 | Leader |
|---|---|---|---|
| Design Arena: websites | 835 | 1313 | Claude Fable 5.1 |
| Design Arena: UI components | Not measured | 1339 | Only Claude Fable 5.1 measured |
| Design Arena: game dev | Not measured | 1381 | Only Claude Fable 5.1 measured |
| Design Arena: data viz | Not measured | 1344 | Only Claude Fable 5.1 measured |
| Design Arena: 3D | Not measured | 1393 | Only Claude Fable 5.1 measured |
| Design Arena: all code categories | Not measured | 1336 | Only Claude Fable 5.1 measured |
| Design Arena: SVG | Not measured | 1301 | Only Claude Fable 5.1 measured |
| Design Arena: ASCII art | Not measured | 1323 | Only Claude Fable 5.1 measured |
| LiveBench design | Not measured | 83.4% | Only Claude Fable 5.1 measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Nova Premier 1.0 | Claude Fable 5.1 | Leader |
|---|---|---|---|
| LiveBench data analysis | Not measured | 80.3% | Only Claude Fable 5.1 measured |
| Public Benefits Bench (Vals AI) | Not measured | 74.9% | Only Claude Fable 5.1 measured |
| SAGE (Vals AI) | Not measured | 48.5% | Only Claude Fable 5.1 measured |
| MedScribe (Vals AI) | Not measured | 91.3% | Only Claude Fable 5.1 measured |
| IFBench | 36.2% | Not measured | Only Nova Premier 1.0 measured |
| Long context reasoning (AA-LCR) | 34.3% | 85.3% | Claude Fable 5.1 |
| DTBench | Not measured | 97.6% | Only Claude Fable 5.1 measured |
| LMCA | Not measured | 65.5% | Only Claude Fable 5.1 measured |
| Furniture assembly | Not measured | 70.0% | Only Claude Fable 5.1 measured |
| LMArena Text | Not measured | 1512 | Only Claude Fable 5.1 measured |
| LMArena Text: instruction following | Not measured | 1518 | Only Claude Fable 5.1 measured |
| LMArena Text: creative writing | Not measured | 1509 | Only Claude Fable 5.1 measured |
| LMArena Vision | Not measured | 1319 | Only Claude Fable 5.1 measured |
| LMArena Text: English | Not measured | 1506 | Only Claude Fable 5.1 measured |
| LMArena Text: non-English | Not measured | 1508 | Only Claude Fable 5.1 measured |
| LMArena Text: Chinese | Not measured | 1584 | Only Claude Fable 5.1 measured |
| LMArena Text: German | Not measured | 1499 | Only Claude Fable 5.1 measured |
| LMArena Text: Japanese | Not measured | 1562 | Only Claude Fable 5.1 measured |
| LMArena Text: Korean | Not measured | 1517 | Only Claude Fable 5.1 measured |
| LMArena Text: French | Not measured | 1523 | Only Claude Fable 5.1 measured |
| LMArena Text: Spanish | Not measured | 1520 | Only Claude Fable 5.1 measured |
| LMArena Text: Russian | Not measured | 1520 | Only Claude Fable 5.1 measured |
| LMArena Text: Polish | Not measured | 1525 | Only Claude Fable 5.1 measured |
| LMArena Text: multi-turn | Not measured | 1493 | Only Claude Fable 5.1 measured |
| LMArena Text: longer queries | Not measured | 1524 | Only Claude Fable 5.1 measured |
| LMArena Text: writing and language | Not measured | 1510 | Only Claude Fable 5.1 measured |
| LMArena Text: entertainment and media | Not measured | 1497 | Only Claude Fable 5.1 measured |
| LMArena Vision: English | Not measured | 1313 | Only Claude Fable 5.1 measured |
| LMArena Vision: Chinese | Not measured | 1391 | Only Claude Fable 5.1 measured |
| LMArena Vision: reading text | Not measured | 1327 | Only Claude Fable 5.1 measured |
| LMArena Vision: humor | Not measured | 1318 | Only Claude Fable 5.1 measured |
| LMArena Vision: creative writing | Not measured | 1330 | Only Claude Fable 5.1 measured |
| Neither model has a result on the other 14 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Nova Premier 1.0 | Claude Fable 5.1 | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Nova Premier 1.0$0.0088Fits in one request
Claude Fable 5.1$0.035Fits in one request
Nova Premier 1.0 costs less
Repository review
50K input + 3K output tokens
Nova Premier 1.0$0.163Fits in one request
Claude Fable 5.1$0.650Fits in one request
Nova Premier 1.0 costs less
Agent loop
200K input + 10K output tokens
Nova Premier 1.0$0.625Fits in one request
Claude Fable 5.1$2.50Fits in one request
Nova Premier 1.0 costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Amazon Nova Premier 1.0 | Anthropic Claude Fable 5.1 |
|---|---|---|
| Maker | Amazon | Anthropic |
| Weights | No public weights listed | No public weights listed |
| Released | October 31, 2025 | September 1, 2026 |
| Context window | 1M | 1M |
| Input $/Mtok | $2.50 | $10.00 |
| Output $/Mtok | $12.50 | $50.00 |
| Coding index | Not benchmarked | 84.2 |
| Independent measurements behind it | 0 | 5 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Nova Premier 1.0 better than Claude Fable 5.1 for coding?
Only Claude Fable 5.1 has a coding score, 84.2 on the Vibe Coding Index; Nova Premier 1.0 has none, so the two cannot be ranked on coding. Pick Nova Premier 1.0 for output tokens 4.0x cheaper ($12.50 vs $50.00 per million).
Which is cheaper, Nova Premier 1.0 or Claude Fable 5.1?
Nova Premier 1.0 costs $2.50 per million input tokens and $12.50 per million output tokens; Claude Fable 5.1 costs $10.00 and $50.00. Cost per solved task is known for neither of them.
Which has the bigger context window, Nova Premier 1.0 or Claude Fable 5.1?
Neither: both take 1M tokens.
How many benchmarks is the Nova Premier 1.0 vs Claude Fable 5.1 comparison based on?
6 benchmarks have a result for both models as of October 21, 2026. Nova Premier 1.0's coding index rests on 0 independent benchmarks and Claude Fable 5.1's on 5. Where only one model has a result, the page says so instead of naming a winner.