Model comparison
DeepSeek LLM 67B vs Inkling-Small
Inkling-Small is the stronger model overall, scoring 46.5 to 24.9 on the Noometry Index.
Last verified . 14 shared benchmarks.
DeepSeekSummary
- They share 14 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Inkling-Small in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling-Small leads 48.2 to 7.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 90% for Inkling-Small.
Side by side
| DeepSeek LLM 67B | Inkling-Small | |
|---|---|---|
| Provider | DeepSeek | Thinking Machines Lab |
| Noometry Index | 24.9 | 46.5 |
| Released | 2023-11-29 | 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 | 15 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
DeepSeek LLM 67B: 31.9 (#278), Inkling-Small: 43.6 (#85)
| Benchmark | DeepSeek LLM 67B | Inkling-Small |
|---|---|---|
| LMArena Coding | 1096 | 1451 |
| LMArena WebDev | — | 1409 |
| SciCode | — | 48.7% |
Reasoning Inkling-Small leads
DeepSeek LLM 67B: 16.5 (#304), Inkling-Small: 38.6 (#63)
| Benchmark | DeepSeek LLM 67B | Inkling-Small |
|---|---|---|
| Chess Puzzles | 0% | 18% |
| LMArena Hard Prompts | 1070 | 1423 |
| Epoch Capabilities Index | 110.5 | 150.15 |
| ARC-AGI-2 | — | 40.1% |
| ARC-AGI-1 | — | 84% |
| CritPt | — | 8.3% |
| Mystery Game Puzzles | — | 6% |
Math Inkling-Small leads
DeepSeek LLM 67B: 8.7 (#324), Inkling-Small: 45.1 (#77)
| Benchmark | DeepSeek LLM 67B | Inkling-Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 90% |
| LMArena Math | 1108 | 1459 |
| FrontierMath (Tiers 1-3) | — | 46.3% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 6% |
| MATH Level 5 | 6.4% | — |
Knowledge Inkling-Small leads
DeepSeek LLM 67B: 7.0 (#313), Inkling-Small: 48.2 (#77)
| Benchmark | DeepSeek LLM 67B | Inkling-Small |
|---|---|---|
| GPQA Diamond | 24.6% | 88.5% |
| SimpleQA Verified | — | 19.1% |
| LMArena Expert | — | 1442 |
Multimodal Not comparable
DeepSeek LLM 67B: —, Inkling-Small: 39.1 (#62)
| Benchmark | DeepSeek LLM 67B | Inkling-Small |
|---|---|---|
| LMArena Vision | — | 1235 |
Multilingual Inkling-Small leads
DeepSeek LLM 67B: 29.4 (#267), Inkling-Small: 51.7 (#104)
| Benchmark | DeepSeek LLM 67B | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1073 | 1402 |
| LMArena Chinese | 1132 | 1465 |
| LMArena French | — | 1436 |
| LMArena German | — | 1405 |
| LMArena Japanese | — | 1405 |
| LMArena Korean | — | 1363 |
| LMArena Russian | — | 1391 |
| LMArena Spanish | — | 1428 |
Instruction Following Inkling-Small leads
DeepSeek LLM 67B: 55.4 (#277), Inkling-Small: 73.8 (#114)
| Benchmark | DeepSeek LLM 67B | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1079 | 1399 |
Long Context Inkling-Small leads
DeepSeek LLM 67B: 33.1 (#265), Inkling-Small: 42.7 (#118)
| Benchmark | DeepSeek LLM 67B | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1092 | 1401 |
Writing & Preference Inkling-Small leads
DeepSeek LLM 67B: 31.6 (#282), Inkling-Small: 59.6 (#107)
| Benchmark | DeepSeek LLM 67B | Inkling-Small |
|---|---|---|
| LMArena Text | 1105 | 1414 |
| LMArena Creative Writing | 1067 | 1331 |
| LMArena Multi-Turn | 1082 | 1418 |
| EQ-Bench Creative Writing | — | 1491 |
Frequently asked questions
Is DeepSeek LLM 67B better than Inkling-Small?
Inkling-Small is the stronger model overall, scoring 46.5 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Inkling-Small better for coding?
Inkling-Small scores higher on coding benchmarks: 43.6 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Inkling-Small share?
14 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Inkling-Small has 33.