Model comparison
Claude Fable 5 vs Gemini 4 Argon
Claude Fable 5 is the stronger model overall, scoring 66.8 to 56.5 on the Noometry Index.
Last verified . 21 shared benchmarks.
GoogleSummary
- They share 21 benchmarks with published results for both. Claude Fable 5 scores higher in 6 categories and Gemini 4 Argon in 4 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Fable 5 leads 76.8 to 44.2.
- The biggest single-benchmark swing is APEX-Agents: 63.6% for Claude Fable 5 and 82.2% for Gemini 4 Argon.
Side by side
| Claude Fable 5 | Gemini 4 Argon | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 66.8 | 56.5 |
| Released | 2026-06-07 | 2026-09-30 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | — |
| Max output | 128K | — |
| Input $ / M tokens | $10 | — |
| Output $ / M tokens | $50 | — |
| Results tracked | 62 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Fable 5 leads
Claude Fable 5: 70.6 (#4), Gemini 4 Argon: 62.0 (#9)
| Benchmark | Claude Fable 5 | Gemini 4 Argon |
|---|---|---|
| LMArena WebDev | 1625 | 1678 |
| FrontierSWE | 47% | 55% |
| SciCode | 61% | 61.8% |
| LMArena Coding | 1519 | 1550 |
| DeepSWE | 69.9% | — |
| FrontierCode | 53.5% | — |
| GSO | 78.4% | — |
| WeirdML | 91.9% | — |
| MirrorCode | 63.9% | — |
| ALE-Bench | 2,041 | — |
Agentic & Tool Use Claude Fable 5 leads
Claude Fable 5: 54.0 (#2), Gemini 4 Argon: 49.2 (#8)
| Benchmark | Claude Fable 5 | Gemini 4 Argon |
|---|---|---|
| APEX-Agents | 63.6% | 82.2% |
| Vending-Bench 2 | 5,680 | 13,718 |
| Remote Labor Index | 16.1% | — |
| τ²-bench Banking | 39.7% | — |
| PostTrainBench | 41.8% | — |
| GBAEval | 74.5% | — |
| GDP.pdf | 30% | — |
| LMArena Search | 1230 | — |
Reasoning Claude Fable 5 leads
Claude Fable 5: 76.8 (#6), Gemini 4 Argon: 44.2 (#47)
| Benchmark | Claude Fable 5 | Gemini 4 Argon |
|---|---|---|
| CritPt | 28.6% | 27.1% |
| LMArena Hard Prompts | 1508 | 1548 |
| ARC-AGI-2 | 89.2% | — |
| SimpleBench | 81.9% | — |
| Kagi LLM Benchmark | 91.4% | — |
| NYT Connections (extended) | 92.7% | — |
| ARC-AGI-1 | 98.5% | — |
| Chess Puzzles | 41% | — |
| EnigmaEval | 39.3% | — |
| EBR-Bench | 39.5% | — |
| Mystery Game Puzzles | 52% | — |
| DTBench | 98.4% | — |
| LMCA | 61.1% | — |
| Surface Evolver Bench | 95% | — |
| Bench to the Future 3 | 0.13 | — |
| Epoch Capabilities Index | 162.06 | — |
Math Claude Fable 5 leads
Claude Fable 5: 88.5 (#5), Gemini 4 Argon: 73.9 (#17)
| Benchmark | Claude Fable 5 | Gemini 4 Argon |
|---|---|---|
| ProofBench | 95% | 99% |
| LMArena Math | 1519 | 1536 |
| FrontierMath (Tiers 1-3) | 87% | — |
| FrontierMath Tier 4 | 90.2% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| FrontierMath Erdős | 0% | — |
Knowledge Claude Fable 5 leads
Claude Fable 5: 62.2 (#25), Gemini 4 Argon: 43.9 (#89)
| Benchmark | Claude Fable 5 | Gemini 4 Argon |
|---|---|---|
| LMArena Expert | 1534 | 1553 |
| GPQA Diamond | 85.9% | — |
| SimpleQA Verified | 70.7% | — |
Multimodal Gemini 4 Argon leads
Claude Fable 5: 45.3 (#17), Gemini 4 Argon: 46.5 (#14)
| Benchmark | Claude Fable 5 | Gemini 4 Argon |
|---|---|---|
| Blueprint-Bench 2 | 38.6% | 54.4% |
| LMArena Vision | 1324 | — |
| Furniture Assembly | 35.8% | — |
| LMArena Document | 1496 | — |
Multilingual Gemini 4 Argon leads
Claude Fable 5: 57.3 (#9), Gemini 4 Argon: 60.3 (#1)
| Benchmark | Claude Fable 5 | Gemini 4 Argon |
|---|---|---|
| LMArena Non-English | 1481 | 1523 |
| LMArena Chinese | 1543 | 1610 |
| LMArena Russian | 1504 | 1537 |
| LMArena Spanish | 1498 | 1497 |
| LMArena French | 1505 | — |
| LMArena German | 1486 | — |
| LMArena Japanese | 1506 | — |
| LMArena Korean | 1488 | — |
Instruction Following Gemini 4 Argon leads
Claude Fable 5: 78.6 (#8), Gemini 4 Argon: 80.1 (#2)
| Benchmark | Claude Fable 5 | Gemini 4 Argon |
|---|---|---|
| LMArena Instruction Following | 1502 | 1538 |
Long Context Gemini 4 Argon leads
Claude Fable 5: 46.3 (#23), Gemini 4 Argon: 47.6 (#15)
| Benchmark | Claude Fable 5 | Gemini 4 Argon |
|---|---|---|
| LMArena Longer Query | 1509 | 1549 |
Writing & Preference Claude Fable 5 leads
Claude Fable 5: 75.9 (#5), Gemini 4 Argon: 71.4 (#19)
| Benchmark | Claude Fable 5 | Gemini 4 Argon |
|---|---|---|
| LMArena Text | 1491 | 1534 |
| LMArena Creative Writing | 1494 | 1531 |
| LMArena Multi-Turn | 1504 | 1557 |
| EQ-Bench Creative Writing | 1943 | — |
| EQ-Bench 4 | 1340 | — |
Frequently asked questions
Is Claude Fable 5 better than Gemini 4 Argon?
Claude Fable 5 is the stronger model overall, scoring 66.8 to 56.5 on the Noometry Index.
Is Claude Fable 5 or Gemini 4 Argon better for coding?
Claude Fable 5 scores higher on coding benchmarks: 70.6 versus 62.0 in the Noometry coding category.
How many benchmarks do Claude Fable 5 and Gemini 4 Argon share?
21 benchmarks have published results for both models. Claude Fable 5 has 62 scored results on Noometry and Gemini 4 Argon has 21.