Model comparison
Claude Fable 5 vs Llama 3-8B
Claude Fable 5 is the stronger model overall, scoring 66.3 to 25.3 on the Noometry Index. Llama 3-8B costs 143× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.
Last verified . 22 shared benchmarks.
MetaSummary
- They share 22 benchmarks with published results for both. Claude Fable 5 scores higher in 8 categories and Llama 3-8B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Fable 5 leads 88.4 to 8.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 100% for Claude Fable 5 and 1.9% for Llama 3-8B.
- Llama 3-8B is cheaper at $0.14 / $0.14 per million input/output tokens, against $10 / $50 for Claude Fable 5.
- Claude Fable 5 accepts more context: 1M tokens versus 8K.
- Llama 3-8B has downloadable open weights; the other is API-only.
Side by side
| Claude Fable 5 | Llama 3-8B | |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 66.3 | 25.3 |
| Released | 2026-06-07 | 2024-04-18 |
| Weights | Proprietary | Open |
| Context window | 1M | 8K |
| Max output | 128K | 8K |
| Input $ / M tokens | $10 | $0.14 |
| Output $ / M tokens | $50 | $0.14 |
| Results tracked | 61 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Fable 5 leads
Claude Fable 5: 67.0 (#4), Llama 3-8B: 30.5 (#285)
| Benchmark | Claude Fable 5 | Llama 3-8B |
|---|---|---|
| LMArena Coding | 1519 | 1152 |
| DeepSWE | 69.9% | — |
| FrontierCode | 53.5% | — |
| LMArena WebDev | 1626 | — |
| FrontierSWE | 47% | — |
| SciCode | 61% | — |
| WeirdML | 91.9% | — |
| BigCodeBench Instruct | — | 31.9% |
| MirrorCode | 63.9% | — |
| BigCodeBench Complete | — | 36.9% |
| ALE-Bench | 2,041 | — |
| HumanEval+ | — | 56.7% |
| MBPP+ | — | 54.8% |
Agentic & Tool Use Not comparable
Claude Fable 5: 54.1 (#2), Llama 3-8B: —
| Benchmark | Claude Fable 5 | Llama 3-8B |
|---|---|---|
| APEX-Agents | 63.6% | — |
| Remote Labor Index | 16.1% | — |
| τ²-bench Banking | 39.7% | — |
| PostTrainBench | 41.8% | — |
| GBAEval | 74.5% | — |
| GDP.pdf | 30% | — |
| LMArena Search | 1230 | — |
| Vending-Bench 2 | 5,680 | — |
Reasoning Claude Fable 5 leads
Claude Fable 5: 76.8 (#4), Llama 3-8B: 13.8 (#321)
| Benchmark | Claude Fable 5 | Llama 3-8B |
|---|---|---|
| Chess Puzzles | 41% | 0% |
| LMArena Hard Prompts | 1508 | 1133 |
| DTBench | 98.4% | 43.9% |
| Epoch Capabilities Index | 163.6 | 116.33 |
| ARC-AGI-2 | 89.2% | — |
| SimpleBench | 81.9% | — |
| Kagi LLM Benchmark | 91.4% | — |
| NYT Connections (extended) | 92.7% | — |
| ARC-AGI-1 | 98.5% | — |
| CritPt | 28.6% | — |
| EnigmaEval | 39.3% | — |
| EBR-Bench | 39.5% | — |
| Mystery Game Puzzles | 52% | — |
| LMCA | 61.1% | — |
| Surface Evolver Bench | 95% | — |
| Adversarial NLI | — | 57.3% |
| Bench to the Future 3 | 0.13 | — |
| ForecastBench | — | 58.6 |
| WinoGrande | — | 75.7% |
Math Claude Fable 5 leads
Claude Fable 5: 88.4 (#5), Llama 3-8B: 8.3 (#317)
| Benchmark | Claude Fable 5 | Llama 3-8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 1.9% |
| LMArena Math | 1519 | 1151 |
| FrontierMath (Tiers 1-3) | 87% | — |
| FrontierMath Tier 4 | 90.2% | — |
| ProofBench | 95% | — |
| MATH Level 5 | — | 6.1% |
| FrontierMath Erdős | 0% | — |
Knowledge Claude Fable 5 leads
Claude Fable 5: 62.3 (#22), Llama 3-8B: 7.8 (#303)
| Benchmark | Claude Fable 5 | Llama 3-8B |
|---|---|---|
| GPQA Diamond | 85.9% | 26.1% |
| LMArena Expert | 1534 | 1113 |
| SimpleQA Verified | 70.7% | — |
| ARC (AI2) Challenge | — | 82.8% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 82.6% |
| TriviaQA | — | 67.7% |
Multimodal Not comparable
Claude Fable 5: 45.6 (#14), Llama 3-8B: —
| Benchmark | Claude Fable 5 | Llama 3-8B |
|---|---|---|
| LMArena Vision | 1326 | — |
| Blueprint-Bench 2 | 38.6% | — |
| Furniture Assembly | 35.8% | — |
| LMArena Document | 1496 | — |
Multilingual Claude Fable 5 leads
Claude Fable 5: 57.6 (#8), Llama 3-8B: 31.0 (#256)
| Benchmark | Claude Fable 5 | Llama 3-8B |
|---|---|---|
| LMArena Non-English | 1483 | 1098 |
| LMArena Chinese | 1546 | 1076 |
| LMArena French | 1509 | 1158 |
| LMArena German | 1486 | 1104 |
| LMArena Japanese | 1507 | 967 |
| LMArena Korean | 1493 | 1003 |
| LMArena Russian | 1507 | 1109 |
| LMArena Spanish | 1503 | 1172 |
Instruction Following Claude Fable 5 leads
Claude Fable 5: 78.8 (#7), Llama 3-8B: 58.7 (#255)
| Benchmark | Claude Fable 5 | Llama 3-8B |
|---|---|---|
| LMArena Instruction Following | 1503 | 1127 |
Long Context Claude Fable 5 leads
Claude Fable 5: 46.3 (#22), Llama 3-8B: 34.2 (#246)
| Benchmark | Claude Fable 5 | Llama 3-8B |
|---|---|---|
| LMArena Longer Query | 1510 | 1128 |
Writing & Preference Claude Fable 5 leads
Claude Fable 5: 76.1 (#5), Llama 3-8B: 37.7 (#251)
| Benchmark | Claude Fable 5 | Llama 3-8B |
|---|---|---|
| LMArena Text | 1491 | 1166 |
| LMArena Creative Writing | 1494 | 1150 |
| LMArena Multi-Turn | 1505 | 1152 |
| EQ-Bench Creative Writing | 1943 | — |
| EQ-Bench 4 | 1340 | — |
Frequently asked questions
Is Claude Fable 5 better than Llama 3-8B?
Claude Fable 5 is the stronger model overall, scoring 66.3 to 25.3 on the Noometry Index. Llama 3-8B costs 143× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.
Which is cheaper, Claude Fable 5 or Llama 3-8B?
Llama 3-8B is cheaper. It lists at $0.14 per million input tokens and $0.14 per million output tokens; Claude Fable 5 lists at $10 and $50.
Is Claude Fable 5 or Llama 3-8B better for coding?
Claude Fable 5 scores higher on coding benchmarks: 67.0 versus 30.5 in the Noometry coding category.
Which has the bigger context window?
Claude Fable 5 does, with 1M tokens against 8K.
How many benchmarks do Claude Fable 5 and Llama 3-8B share?
22 benchmarks have published results for both models. Claude Fable 5 has 61 scored results on Noometry and Llama 3-8B has 34.