Claude Fable 5.1 vs Gemini 4 Carbon
Gemini 4 Carbon leads Claude Fable 5.1 on coding, 86.6 to 82.8 on the Vibe Coding Index, and Gemini 4 Carbon costs 5.0x less per output token ($10.00 vs $50.00 per million). Updated November 14, 2026; 69 benchmarks have a result for both.
vs boards won of 69 shared, 1 tied
Claude Fable 5.1 or Gemini 4 Carbon: which to pick
Pick Gemini 4 Carbon for coding: it scores 86.6 on the Vibe Coding Index against 82.8 for Claude Fable 5.1, though on 4 benchmarks against 5.
Pick Claude Fable 5.1 for work measured by Vibe Code Bench (Vals AI) or Design Arena: spreadsheets, where it leads.
Model AClaude Fable 5.1Anthropic82.8/1005 independent benchmarksNo cost per solved taskModel BGemini 4 CarbonGoogle86.6/1004 independent benchmarksNo cost per solved task
- Shared results
- 69
- Claude Fable 5.1 only
- 79
- Gemini 4 Carbon only
- 4
- Like-for-like categories
- 8 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
Gemini 4 Carbon
Gemini 4 Carbon scores 86.6 against 82.8.
5 and 4 benchmarks behind the scores
Intelligence
AA Intelligence Index
Gemini 4 Carbon
Gemini 4 Carbon leads, 60.0 against 50.0.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Claude Fable 5.1 has a AA Agentic Index result, 57.2.
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
Gemini 4 Carbon
Gemini 4 Carbon leads, 1319 against 1305.
Same board, both measured
General
Vals Index
No call
Only Gemini 4 Carbon has a Vals Index result, 70.5%.
Directional only
Long documents
Listed context window
Gemini 4 Carbon
Gemini 4 Carbon takes 1.05M tokens against 1M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Gemini 4 Carbon
Claude Fable 5.1 $0.035, Gemini 4 Carbon $0.0070 per turn.
List prices
At a glance
- Coding index
- Claude Fable 5.1 82.8 from 5 benchmarks, Gemini 4 Carbon 86.6 from 4 benchmarks.
- Widest category
- Agentic work, 13.1 points apart on average over 9 shared benchmarks.
- Widest single gap
- Vending-Bench 2: Claude Fable 5.1 $5,422 against Gemini 4 Carbon $16,484, 66.1 points apart on a 0 to 100 scale.
- Output price
- Claude Fable 5.1 $50.00 against Gemini 4 Carbon $10.00 per million output tokens, 5.0x apart.
- Context window
- Claude Fable 5.1 takes 1M tokens, Gemini 4 Carbon 1.05M.
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 | Claude Fable 5.1 | Bars | Gemini 4 Carbon | Ties |
|---|---|---|---|---|
| Coding | 1 | 12 | ||
| Intelligence | 0 | 2 | ||
| Agentic work | 3 | 6 | ||
| Reasoning | 1 | 11 | ||
| Math | 1 | 3 | 1 tie | |
| Knowledge | 1 | 6 | ||
| Web design | 2 | 4 | ||
| General | 2 | 13 | ||
| All shared boards | 11 | 57 | 1 tie |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index112
| Benchmark | Claude Fable 5.1 | Gemini 4 Carbon | Leader |
|---|---|---|---|
| LiveBench coding | 89.7% | 91.0% | Gemini 4 Carbon |
| LMArena WebDev | 1742 | 1768 | Gemini 4 Carbon |
| AA Coding Index | 80.7 | Not measured | Only Claude Fable 5.1 measured |
| LiveCodeBench (Vals AI) | 90.5% | Not measured | Only Claude Fable 5.1 measured |
| Terminal-Bench 4 (Vals AI) | 58.1% | 63.1% | Gemini 4 Carbon |
| Vibe Code Bench (Vals AI) | 90.3% | 89.1% | Claude Fable 5.1 |
| Code migration (Vals AI) | 54.6% | Not measured | Only Claude Fable 5.1 measured |
| ProgramBench (Vals AI) | 7.0% | Not measured | Only Claude Fable 5.1 measured |
| IOI (Vals AI) | 90.8% | Not measured | Only Claude Fable 5.1 measured |
| Terminal-Bench 2.1 (Vals AI) | 85.0% | Not measured | Only Claude Fable 5.1 measured |
| SWE-bench Multimodal (Vals AI) | 61.3% | Not measured | Only Claude Fable 5.1 measured |
| Vibe Code Bench 1-100 (Vals AI) | 28.0% | Not measured | Only Claude Fable 5.1 measured |
| SkillsBench (Vals AI) | 61.5% | Not measured | Only Claude Fable 5.1 measured |
| CyberBench (Vals AI) | 70.4% | Not measured | Only Claude Fable 5.1 measured |
| SciCode | 63.1% | Not measured | Only Claude Fable 5.1 measured |
| Terminal-Bench 4.0 (Artificial Analysis run) | 55.1% | 65.2% | Gemini 4 Carbon |
| FrontierCode 2.0 | 35.7% | 40.6% | Gemini 4 Carbon |
| FrontierCode | 50.9% | Not measured | Only Claude Fable 5.1 measured |
| FrontierSWE | 56.3% | 61.2% | Gemini 4 Carbon |
| GSO-Bench | 88.2% | Not measured | Only Claude Fable 5.1 measured |
| WeirdML | 92.9% | Not measured | Only Claude Fable 5.1 measured |
| MirrorCode | 93.3% | Not measured | Only Claude Fable 5.1 measured |
| ALE-Bench | 2143.2 | 2374.7 | Gemini 4 Carbon |
| LMArena Text: coding | 1527 | 1564 | Gemini 4 Carbon |
| LMArena Text: software and IT | 1525 | 1552 | Gemini 4 Carbon |
| LMArena WebDev: React | 1787 | 1792 | Gemini 4 Carbon |
| LMArena WebDev: HTML | 1681 | 1770 | Gemini 4 Carbon |
| LMArena WebDev: from an image | 1724 | Not measured | Only Claude Fable 5.1 measured |
| SWE-Bench Pro V2 | 99.1% | Not measured | Only Claude Fable 5.1 measured |
| SWE Atlas: Codebase QnA | 60.0% | Not measured | Only Claude Fable 5.1 measured |
| SWE Atlas: Refactoring | 56.7% | Not measured | Only Claude Fable 5.1 measured |
| SWE Atlas: Test Writing | 67.0% | Not measured | Only Claude Fable 5.1 measured |
| GameBench 2 | 94.0 | Not measured | Only Claude Fable 5.1 measured |
| Terminal-Bench 4.0 | 57.9% | Not measured | Only Claude Fable 5.1 measured |
| CursorBench 4.0 | 51.8% | 60.4% | Gemini 4 Carbon |
| ProgramBench | 9.0% | Not measured | Only Claude Fable 5.1 measured |
| Neither model has a result on the other 16 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Claude Fable 5.1 | Gemini 4 Carbon | Leader |
|---|---|---|---|
| AA Intelligence Index | 50.0 | 60.0 | Gemini 4 Carbon |
| Epoch Capabilities Index | 167.0 | 169.8 | Gemini 4 Carbon |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index36
| Benchmark | Claude Fable 5.1 | Gemini 4 Carbon | Leader |
|---|---|---|---|
| AA Agentic Index | 57.2 | Not measured | Only Claude Fable 5.1 measured |
| Design Arena: agents building web apps | 1315 | Not measured | Only Claude Fable 5.1 measured |
| Design Arena: agents building full-stack apps | 1301 | Not measured | Only Claude Fable 5.1 measured |
| Design Arena: agents building mobile apps | 1253 | 1284 | Gemini 4 Carbon |
| Design Arena: agents building Godot games | 1304 | Not measured | Only Claude Fable 5.1 measured |
| Design Arena: HTML slides | 1390 | Not measured | Only Claude Fable 5.1 measured |
| Design Arena: PowerPoint slides | 1316 | Not measured | Only Claude Fable 5.1 measured |
| Design Arena: spreadsheets | 1346 | 1224 | Claude Fable 5.1 |
| LiveBench research | 88.5% | 92.5% | Gemini 4 Carbon |
| LiveBench browser | 89.8% | 80.0% | Claude Fable 5.1 |
| LiveBench long agentic | 74.2% | 72.7% | Claude Fable 5.1 |
| SREBench (Vals AI) | 22.9% | Not measured | Only Claude Fable 5.1 measured |
| Finance Agent (Vals AI) | 58.9% | Not measured | Only Claude Fable 5.1 measured |
| Tax Agent Bench (Vals AI) | 50.7% | 51.8% | Gemini 4 Carbon |
| Legal Research Bench (Vals AI) | 55.3% | 55.8% | Gemini 4 Carbon |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 17.5% | Only Gemini 4 Carbon measured |
| Excel Modeling Benchmark (Vals AI) | 76.7% | Not measured | Only Claude Fable 5.1 measured |
| Terminal-Bench-Science (Vals AI) | 40.0% | Not measured | Only Claude Fable 5.1 measured |
| Time Horizon Index (Vals AI) | 63.3% | Not measured | Only Claude Fable 5.1 measured |
| CUA-bench (Vals AI) | 13.2% | Not measured | Only Claude Fable 5.1 measured |
| Robo-bench (Vals AI) | 5.8% | Not measured | Only Claude Fable 5.1 measured |
| APEX-Agents | 68.6% | 84.2% | Gemini 4 Carbon |
| Remote Labor Index | 17.9% | Not measured | Only Claude Fable 5.1 measured |
| PostTrainBench | 44.6% | Not measured | Only Claude Fable 5.1 measured |
| SpireClimb | 2.0% | Not measured | Only Claude Fable 5.1 measured |
| Vending-Bench 2 | $5,422 | $16,484 | Gemini 4 Carbon |
| LMArena Search | 1237 | Not measured | Only Claude Fable 5.1 measured |
| MCP Atlas | 87.2% | Not measured | 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 index111
| Benchmark | Claude Fable 5.1 | Gemini 4 Carbon | Leader |
|---|---|---|---|
| GPQA Diamond | 93.4% | Not measured | Only Claude Fable 5.1 measured |
| LiveBench reasoning | 91.7% | 90.6% | Claude Fable 5.1 |
| MysteryMechanism (Vals AI) | 47.8% | Not measured | Only Claude Fable 5.1 measured |
| MMMU Pro (Vals AI) | 90.6% | Not measured | Only Claude Fable 5.1 measured |
| GPQA Diamond (Artificial Analysis run) | 93.7% | Not measured | Only Claude Fable 5.1 measured |
| Humanity's Last Exam (Artificial Analysis run) | 59.1% | Not measured | Only Claude Fable 5.1 measured |
| HLE-Diamond (Artificial Analysis run) | 60.1% | 69.1% | Gemini 4 Carbon |
| CritPt v2, hard subset (Artificial Analysis run) | 62.0% | 69.0% | Gemini 4 Carbon |
| GPQA Diamond (Epoch AI run) | Not measured | 96.5% | Only Gemini 4 Carbon measured |
| ARC-AGI | 97.5% | 98.5% | Gemini 4 Carbon |
| ARC-AGI-2 | 90.0% | 94.2% | Gemini 4 Carbon |
| SimpleBench | 86.6% | 92.6% | Gemini 4 Carbon |
| Chess puzzles | 48.0% | 78.0% | Gemini 4 Carbon |
| Mystery game puzzles | 58.0% | 73.0% | Gemini 4 Carbon |
| EBR-bench | 57.1% | 87.6% | Gemini 4 Carbon |
| LMArena Text: hard prompts | 1527 | 1551 | Gemini 4 Carbon |
| LMArena Text: expert | 1546 | 1582 | Gemini 4 Carbon |
| LMArena Text: hard prompts in English | 1522 | 1545 | Gemini 4 Carbon |
| LMArena Vision: diagrams | 1346 | Not measured | Only Claude Fable 5.1 measured |
| LMArena Vision: homework | 1339 | Not measured | Only Claude Fable 5.1 measured |
| Humanity's Last Exam (Scale run) | 51.3% | Not measured | Only Claude Fable 5.1 measured |
| GoBench | 2268 | Not measured | Only Claude Fable 5.1 measured |
| Neither model has a result on the other 4 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index13
| Benchmark | Claude Fable 5.1 | Gemini 4 Carbon | Leader |
|---|---|---|---|
| OTIS Mock AIME | 100.0% | 100.0% | Tie |
| FrontierMath, tiers 1 to 3 | 90.2% | 90.5% | Gemini 4 Carbon |
| FrontierMath, tier 4 | 87.8% | 95.1% | Gemini 4 Carbon |
| ProofBench | 100.0% | Not measured | Only Claude Fable 5.1 measured |
| LMArena Text: math | 1530 | Not measured | Only Claude Fable 5.1 measured |
| LMArena Text: mathematical work | 1542 | 1538 | Claude Fable 5.1 |
| MathArena | 73.6% | 85.4% | Gemini 4 Carbon |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index16
| Benchmark | Claude Fable 5.1 | Gemini 4 Carbon | Leader |
|---|---|---|---|
| MMLU Pro | 92.4% | Not measured | Only Claude Fable 5.1 measured |
| LegalBench (Vals AI) | 88.5% | Not measured | Only Claude Fable 5.1 measured |
| TaxEval (Vals AI) | 76.0% | Not measured | Only Claude Fable 5.1 measured |
| MortgageTax (Vals AI) | 70.8% | Not measured | Only Claude Fable 5.1 measured |
| MedCode (Vals AI) | 53.5% | Not measured | Only Claude Fable 5.1 measured |
| AA-Omniscience | 46.3 | 53.5 | Gemini 4 Carbon |
| SimpleQA Verified | 70.8% | 77.7% | Gemini 4 Carbon |
| GeoBench | 84.0% | Not measured | Only Claude Fable 5.1 measured |
| LMArena Text: science | 1535 | 1535 | Gemini 4 Carbon |
| LMArena Text: medicine and healthcare | 1529 | 1525 | Claude Fable 5.1 |
| LMArena Text: legal and government | 1516 | 1542 | Gemini 4 Carbon |
| LMArena Text: business and finance | 1494 | 1520 | Gemini 4 Carbon |
| FACTS Benchmark Suite | Not measured | 78.4% | Only Gemini 4 Carbon measured |
| PRBench Finance | 50.8% | Not measured | Only Claude Fable 5.1 measured |
| PRBench Legal | 51.6% | 53.3% | Gemini 4 Carbon |
| Neither model has a result on the other 6 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index24
| Benchmark | Claude Fable 5.1 | Gemini 4 Carbon | Leader |
|---|---|---|---|
| Design Arena: websites | 1305 | 1319 | Gemini 4 Carbon |
| Design Arena: UI components | 1332 | 1357 | Gemini 4 Carbon |
| Design Arena: game dev | 1364 | 1326 | Claude Fable 5.1 |
| Design Arena: data viz | 1345 | Not measured | Only Claude Fable 5.1 measured |
| Design Arena: 3D | 1387 | 1434 | Gemini 4 Carbon |
| Design Arena: all code categories | 1330 | 1348 | Gemini 4 Carbon |
| Design Arena: SVG | 1292 | Not measured | Only Claude Fable 5.1 measured |
| Design Arena: ASCII art | 1318 | Not measured | Only Claude Fable 5.1 measured |
| LiveBench design | 81.6% | 80.2% | Claude Fable 5.1 |
GeneralLike-for-likePublic boards, shown as published, kept out of the index213
| Benchmark | Claude Fable 5.1 | Gemini 4 Carbon | Leader |
|---|---|---|---|
| Vals Index | Not measured | 70.5% | Only Gemini 4 Carbon measured |
| LiveBench data analysis | 80.3% | 86.5% | Gemini 4 Carbon |
| Public Benefits Bench (Vals AI) | 74.9% | Not measured | Only Claude Fable 5.1 measured |
| MedScribe (Vals AI) | 91.3% | Not measured | Only Claude Fable 5.1 measured |
| Long context reasoning (AA-LCR) | 85.3% | 79.3% | Claude Fable 5.1 |
| GDPval-AA | 1765 | 1733 | Claude Fable 5.1 |
| DTBench | 97.6% | Not measured | Only Claude Fable 5.1 measured |
| LMCA | 65.5% | Not measured | Only Claude Fable 5.1 measured |
| Furniture assembly | 70.0% | 77.5% | Gemini 4 Carbon |
| LMArena Text | 1512 | 1538 | Gemini 4 Carbon |
| LMArena Text: instruction following | 1520 | 1539 | Gemini 4 Carbon |
| LMArena Text: creative writing | 1514 | 1533 | Gemini 4 Carbon |
| LMArena Vision | 1322 | Not measured | Only Claude Fable 5.1 measured |
| LMArena Text: English | 1507 | 1530 | Gemini 4 Carbon |
| LMArena Text: non-English | 1507 | 1534 | Gemini 4 Carbon |
| LMArena Text: Chinese | 1582 | 1613 | Gemini 4 Carbon |
| LMArena Text: German | 1503 | Not measured | Only Claude Fable 5.1 measured |
| LMArena Text: Japanese | 1560 | Not measured | Only Claude Fable 5.1 measured |
| LMArena Text: Korean | 1505 | Not measured | Only Claude Fable 5.1 measured |
| LMArena Text: French | 1515 | Not measured | Only Claude Fable 5.1 measured |
| LMArena Text: Spanish | 1510 | Not measured | Only Claude Fable 5.1 measured |
| LMArena Text: Russian | 1518 | 1560 | Gemini 4 Carbon |
| LMArena Text: Polish | 1537 | Not measured | Only Claude Fable 5.1 measured |
| LMArena Text: multi-turn | 1492 | 1569 | Gemini 4 Carbon |
| LMArena Text: longer queries | 1523 | 1549 | Gemini 4 Carbon |
| LMArena Text: writing and language | 1515 | 1542 | Gemini 4 Carbon |
| LMArena Text: entertainment and media | 1498 | 1527 | Gemini 4 Carbon |
| LMArena Vision: English | 1316 | Not measured | Only Claude Fable 5.1 measured |
| LMArena Vision: Chinese | 1397 | Not measured | Only Claude Fable 5.1 measured |
| LMArena Vision: reading text | 1329 | Not measured | Only Claude Fable 5.1 measured |
| LMArena Vision: humor | 1326 | Not measured | Only Claude Fable 5.1 measured |
| LMArena Vision: creative writing | 1325 | Not measured | Only Claude Fable 5.1 measured |
| LMArena Document | 1515 | Not measured | Only Claude Fable 5.1 measured |
| Neither model has a result on the other 16 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Fable 5.1 | Gemini 4 Carbon | 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
Claude Fable 5.1$0.035Fits in one request
Gemini 4 Carbon$0.0070Fits in one request
Gemini 4 Carbon costs less
Repository review
50K input + 3K output tokens
Claude Fable 5.1$0.650Fits in one request
Gemini 4 Carbon$0.130Fits in one request
Gemini 4 Carbon costs less
Agent loop
200K input + 10K output tokens
Claude Fable 5.1$2.50Fits in one request
Gemini 4 Carbon$0.500Fits in one request
Gemini 4 Carbon 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 | Anthropic Claude Fable 5.1 | Google Gemini 4 Carbon |
|---|---|---|
| Maker | Anthropic | |
| Weights | No public weights listed | No public weights listed |
| Released | September 1, 2026 | November 10, 2026 |
| Context window | 1M | 1.05M |
| Input $/Mtok | $10.00 | $2.00 |
| Output $/Mtok | $50.00 | $10.00 |
| Coding index | 82.8 | 86.6 |
| Independent measurements behind it | 5 | 4 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Fable 5.1 better than Gemini 4 Carbon for coding?
Pick Gemini 4 Carbon for coding: it scores 86.6 on the Vibe Coding Index against 82.8 for Claude Fable 5.1, though on 4 benchmarks against 5. Pick Claude Fable 5.1 for work measured by Vibe Code Bench (Vals AI) or Design Arena: spreadsheets, where it leads.
Which is cheaper, Claude Fable 5.1 or Gemini 4 Carbon?
Claude Fable 5.1 costs $10.00 per million input tokens and $50.00 per million output tokens; Gemini 4 Carbon costs $2.00 and $10.00. Cost per solved task is known for neither of them.
Which has the bigger context window, Claude Fable 5.1 or Gemini 4 Carbon?
Gemini 4 Carbon, with 1.05M tokens against 1M.
How many benchmarks is the Claude Fable 5.1 vs Gemini 4 Carbon comparison based on?
69 benchmarks have a result for both models as of November 14, 2026. Claude Fable 5.1's coding index rests on 5 independent benchmarks and Gemini 4 Carbon's on 4. Where only one model has a result, the page says so instead of naming a winner.