Model comparison
DeepSeek LLM 67B vs Inkling
Inkling is the stronger model overall, scoring 44.1 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 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling leads 55.1 to 7.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 88.9% for Inkling.
Side by side
| DeepSeek LLM 67B | Inkling | |
|---|---|---|
| Provider | DeepSeek | Thinking Machines Lab |
| Noometry Index | 24.9 | 44.1 |
| Released | 2023-11-29 | 2026-07-15 |
| Weights | Open | Open |
| Context window | — | 66K |
| Max output | — | 66K |
| Input $ / M tokens | — | $1.87 |
| Output $ / M tokens | — | $4.68 |
| Results tracked | 15 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling leads
DeepSeek LLM 67B: 31.9 (#278), Inkling: 34.5 (#234)
| Benchmark | DeepSeek LLM 67B | Inkling |
|---|---|---|
| LMArena Coding | 1096 | 1464 |
| FrontierCode | — | 14% |
| LMArena WebDev | — | 1413 |
| FrontierSWE | — | 4.1% |
| SciCode | — | 47% |
| WeirdML | — | 32.3% |
| ALE-Bench | — | 946 |
Agentic & Tool Use Not comparable
DeepSeek LLM 67B: —, Inkling: 29.6 (#85)
| Benchmark | DeepSeek LLM 67B | Inkling |
|---|---|---|
| APEX-Agents | — | 33.8% |
| τ²-bench Banking | — | 25% |
Reasoning Inkling leads
DeepSeek LLM 67B: 16.5 (#304), Inkling: 40.4 (#56)
| Benchmark | DeepSeek LLM 67B | Inkling |
|---|---|---|
| Chess Puzzles | 0% | 21% |
| LMArena Hard Prompts | 1070 | 1451 |
| Epoch Capabilities Index | 110.5 | 148.54 |
| ARC-AGI-2 | — | 36.5% |
| SimpleBench | — | 50% |
| ARC-AGI-1 | — | 79.5% |
| CritPt | — | 5.4% |
| DTBench | — | 87.5% |
| LMCA | — | 37.6% |
Math Inkling leads
DeepSeek LLM 67B: 8.7 (#324), Inkling: 31.3 (#225)
| Benchmark | DeepSeek LLM 67B | Inkling |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 88.9% |
| LMArena Math | 1108 | 1479 |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| FrontierMath Tier 4 | — | 4.9% |
| ProofBench | — | 0% |
| MATH Level 5 | 6.4% | — |
Knowledge Inkling leads
DeepSeek LLM 67B: 7.0 (#313), Inkling: 55.1 (#49)
| Benchmark | DeepSeek LLM 67B | Inkling |
|---|---|---|
| GPQA Diamond | 24.6% | 88.3% |
| SimpleQA Verified | — | 40.3% |
| LMArena Expert | — | 1465 |
Multilingual Inkling leads
DeepSeek LLM 67B: 29.4 (#267), Inkling: 54.0 (#52)
| Benchmark | DeepSeek LLM 67B | Inkling |
|---|---|---|
| LMArena Non-English | 1073 | 1434 |
| LMArena Chinese | 1132 | 1490 |
| LMArena French | — | 1458 |
| LMArena German | — | 1446 |
| LMArena Japanese | — | 1429 |
| LMArena Korean | — | 1404 |
| LMArena Russian | — | 1429 |
| LMArena Spanish | — | 1448 |
Instruction Following Inkling leads
DeepSeek LLM 67B: 55.4 (#277), Inkling: 75.1 (#71)
| Benchmark | DeepSeek LLM 67B | Inkling |
|---|---|---|
| LMArena Instruction Following | 1079 | 1426 |
Long Context Inkling leads
DeepSeek LLM 67B: 33.1 (#265), Inkling: 43.8 (#86)
| Benchmark | DeepSeek LLM 67B | Inkling |
|---|---|---|
| LMArena Longer Query | 1092 | 1434 |
Writing & Preference Inkling leads
DeepSeek LLM 67B: 31.6 (#282), Inkling: 65.2 (#51)
| Benchmark | DeepSeek LLM 67B | Inkling |
|---|---|---|
| LMArena Text | 1105 | 1441 |
| LMArena Creative Writing | 1067 | 1387 |
| LMArena Multi-Turn | 1082 | 1436 |
| EQ-Bench Creative Writing | — | 1611 |
| EQ-Bench 4 | — | 1226 |
Frequently asked questions
Is DeepSeek LLM 67B better than Inkling?
Inkling is the stronger model overall, scoring 44.1 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Inkling better for coding?
Inkling scores higher on coding benchmarks: 34.5 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Inkling share?
14 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Inkling has 41.