Model comparison
Claude Fable 5.1 vs Codellama 34b Instruct
Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 30.8 on the Noometry Index.
Last verified . 10 shared benchmarks.
MetaSummary
- They share 10 benchmarks with published results for both. Claude Fable 5.1 scores higher in 7 categories and Codellama 34b Instruct in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Fable 5.1 leads 89.6 to 31.0.
- Codellama 34b Instruct has downloadable open weights; the other is API-only.
Side by side
| Claude Fable 5.1 | Codellama 34b Instruct | |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 69.0 | 30.8 |
| Released | 2026-09-01 | — |
| Weights | Proprietary | Open |
| Context window | 1M | — |
| Max output | 128K | — |
| Input $ / M tokens | $10 | — |
| Output $ / M tokens | $50 | — |
| Results tracked | 52 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Fable 5.1 leads
Claude Fable 5.1: 74.7 (#1), Codellama 34b Instruct: 28.5 (#314)
| Benchmark | Claude Fable 5.1 | Codellama 34b Instruct |
|---|---|---|
| LMArena Coding | 1528 | 1046 |
| FrontierCode | 50.9% | — |
| CursorBench | 51.8% | — |
| LMArena WebDev | 1744 | — |
| FrontierSWE | 56.3% | — |
| SciCode | 63.1% | — |
| GSO | 88.2% | — |
| WeirdML | 92.9% | — |
| BigCodeBench Instruct | — | 29% |
| MirrorCode | 73.3% | — |
| BigCodeBench Complete | — | 37.1% |
| ALE-Bench | 2,143 | — |
| HumanEval+ | — | 43.9% |
| MBPP+ | — | 56.3% |
Agentic & Tool Use Not comparable
Claude Fable 5.1: 50.7 (#5), Codellama 34b Instruct: —
| Benchmark | Claude Fable 5.1 | Codellama 34b Instruct |
|---|---|---|
| APEX-Agents | 68.6% | — |
| Remote Labor Index | 17.9% | — |
| GDP.pdf | 29.6% | — |
| Vending-Bench 2 | 5,422 | — |
Reasoning Claude Fable 5.1 leads
Claude Fable 5.1: 76.7 (#7), Codellama 34b Instruct: 19.6 (#255)
| Benchmark | Claude Fable 5.1 | Codellama 34b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1526 | 1032 |
| ARC-AGI-2 | 90% | — |
| NYT Connections (extended) | 90% | — |
| ARC-AGI-1 | 97.5% | — |
| CritPt | 31.1% | — |
| Chess Puzzles | 47% | — |
| EBR-Bench | 57.1% | — |
| Mystery Game Puzzles | 58% | — |
| DTBench | 97.6% | — |
| LMCA | 65.5% | — |
| Epoch Capabilities Index | 164.7 | — |
Math Claude Fable 5.1 leads
Claude Fable 5.1: 89.6 (#4), Codellama 34b Instruct: 31.0 (#230)
| Benchmark | Claude Fable 5.1 | Codellama 34b Instruct |
|---|---|---|
| LMArena Math | 1525 | 1056 |
| FrontierMath (Tiers 1-3) | 90.2% | — |
| FrontierMath Tier 4 | 87.8% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| ProofBench | 100% | — |
| FrontierMath Erdős | 0% | — |
Knowledge Not comparable
Claude Fable 5.1: 69.6 (#6), Codellama 34b Instruct: —
| Benchmark | Claude Fable 5.1 | Codellama 34b Instruct |
|---|---|---|
| Humanity's Last Exam | 46.5% | — |
| SimpleQA Verified | 70.8% | — |
| LMArena Expert | 1535 | — |
Multimodal Not comparable
Claude Fable 5.1: 53.9 (#4), Codellama 34b Instruct: —
| Benchmark | Claude Fable 5.1 | Codellama 34b Instruct |
|---|---|---|
| LMArena Vision | 1318 | — |
| Blueprint-Bench 2 | 41.9% | — |
| Furniture Assembly | 70% | — |
| LMArena Document | 1513 | — |
Multilingual Claude Fable 5.1 leads
Claude Fable 5.1: 59.1 (#3), Codellama 34b Instruct: 25.8 (#284)
| Benchmark | Claude Fable 5.1 | Codellama 34b Instruct |
|---|---|---|
| LMArena Non-English | 1507 | 1011 |
| LMArena Chinese | 1586 | 976 |
| LMArena French | 1525 | — |
| LMArena German | 1500 | — |
| LMArena Japanese | 1543 | — |
| LMArena Korean | 1534 | — |
| LMArena Russian | 1521 | — |
| LMArena Spanish | 1516 | — |
Instruction Following Claude Fable 5.1 leads
Claude Fable 5.1: 79.2 (#6), Codellama 34b Instruct: 52.2 (#291)
| Benchmark | Claude Fable 5.1 | Codellama 34b Instruct |
|---|---|---|
| LMArena Instruction Following | 1517 | 1028 |
Long Context Claude Fable 5.1 leads
Claude Fable 5.1: 46.7 (#20), Codellama 34b Instruct: 30.9 (#284)
| Benchmark | Claude Fable 5.1 | Codellama 34b Instruct |
|---|---|---|
| LMArena Longer Query | 1522 | 1013 |
Writing & Preference Claude Fable 5.1 leads
Claude Fable 5.1: 79.2 (#2), Codellama 34b Instruct: 28.2 (#297)
| Benchmark | Claude Fable 5.1 | Codellama 34b Instruct |
|---|---|---|
| LMArena Text | 1510 | 1066 |
| LMArena Creative Writing | 1507 | 1032 |
| LMArena Multi-Turn | 1492 | 1015 |
| EQ-Bench Creative Writing | 2162 | — |
Frequently asked questions
Is Claude Fable 5.1 better than Codellama 34b Instruct?
Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 30.8 on the Noometry Index.
Is Claude Fable 5.1 or Codellama 34b Instruct better for coding?
Claude Fable 5.1 scores higher on coding benchmarks: 74.7 versus 28.5 in the Noometry coding category.
How many benchmarks do Claude Fable 5.1 and Codellama 34b Instruct share?
10 benchmarks have published results for both models. Claude Fable 5.1 has 52 scored results on Noometry and Codellama 34b Instruct has 14.