Model comparison
Codellama 70b Instruct vs Inkling-Small
Inkling-Small is the stronger model overall, scoring 46.5 to 33.3 on the Noometry Index.
Last verified . 4 shared benchmarks.
MetaSummary
- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 0 categories and Inkling-Small in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Inkling-Small leads 51.7 to 24.9.
Side by side
| Codellama 70b Instruct | Inkling-Small | |
|---|---|---|
| Provider | Meta | Thinking Machines Lab |
| Noometry Index | 33.3 | 46.5 |
| Released | — | 2026-07-15 |
| Weights | Open | Open |
| Context window | — | 524K |
| Max output | — | 1.05M |
| Input $ / M tokens | — | $0.45 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 7 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
Codellama 70b Instruct: 37.0 (#189), Inkling-Small: 43.3 (#80)
| Benchmark | Codellama 70b Instruct | Inkling-Small |
|---|---|---|
| LMArena WebDev | — | 1408 |
| SciCode | — | 48.7% |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1451 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Reasoning Inkling-Small leads
Codellama 70b Instruct: 19.2 (#241), Inkling-Small: 39.0 (#53)
| Benchmark | Codellama 70b Instruct | Inkling-Small |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1424 |
| ARC-AGI-2 | — | 40.1% |
| ARC-AGI-1 | — | 84% |
| CritPt | — | 8.3% |
| Chess Puzzles | — | 18% |
| Mystery Game Puzzles | — | 6% |
| Epoch Capabilities Index | — | 150.13 |
Math Not comparable
Codellama 70b Instruct: —, Inkling-Small: 44.9 (#65)
| Benchmark | Codellama 70b Instruct | Inkling-Small |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 46.3% |
| FrontierMath Tier 4 | — | 17.1% |
| OTIS Mock AIME 2024-2025 | — | 90% |
| ProofBench | — | 6% |
| LMArena Math | — | 1453 |
Knowledge Not comparable
Codellama 70b Instruct: —, Inkling-Small: 48.3 (#71)
| Benchmark | Codellama 70b Instruct | Inkling-Small |
|---|---|---|
| GPQA Diamond | — | 88.5% |
| SimpleQA Verified | — | 19.1% |
| LMArena Expert | — | 1442 |
Multimodal Not comparable
Codellama 70b Instruct: —, Inkling-Small: 38.4 (#59)
| Benchmark | Codellama 70b Instruct | Inkling-Small |
|---|---|---|
| LMArena Vision | — | 1235 |
Multilingual Inkling-Small leads
Codellama 70b Instruct: 24.9 (#283), Inkling-Small: 51.7 (#102)
| Benchmark | Codellama 70b Instruct | Inkling-Small |
|---|---|---|
| LMArena Non-English | 992 | 1400 |
| LMArena Chinese | — | 1458 |
| LMArena French | — | 1438 |
| LMArena German | — | 1412 |
| LMArena Japanese | — | 1399 |
| LMArena Korean | — | 1355 |
| LMArena Russian | — | 1392 |
| LMArena Spanish | — | 1426 |
Instruction Following Inkling-Small leads
Codellama 70b Instruct: 52.1 (#288), Inkling-Small: 73.9 (#112)
| Benchmark | Codellama 70b Instruct | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1024 | 1397 |
Long Context Not comparable
Codellama 70b Instruct: —, Inkling-Small: 42.7 (#113)
| Benchmark | Codellama 70b Instruct | Inkling-Small |
|---|---|---|
| LMArena Longer Query | — | 1401 |
Writing & Preference Inkling-Small leads
Codellama 70b Instruct: 33.6 (#272), Inkling-Small: 59.8 (#102)
| Benchmark | Codellama 70b Instruct | Inkling-Small |
|---|---|---|
| LMArena Text | 1057 | 1413 |
| LMArena Creative Writing | — | 1330 |
| EQ-Bench Creative Writing | — | 1491 |
| LMArena Multi-Turn | — | 1420 |
Frequently asked questions
Is Codellama 70b Instruct better than Inkling-Small?
Inkling-Small is the stronger model overall, scoring 46.5 to 33.3 on the Noometry Index.
Is Codellama 70b Instruct or Inkling-Small better for coding?
Inkling-Small scores higher on coding benchmarks: 43.3 versus 37.0 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and Inkling-Small share?
4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Inkling-Small has 33.