Inkling-Small vs NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4
| Spec | Inkling-Small | NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4 |
|---|---|---|
| Respan Index | 29.4 (#84) | 28.8 (#86) |
| Blended price per 1M | $0.637 | $0.925 |
| Context window | 1M | 1M |
| Input / output per 1M | $0.45 / $1.2 | $0.5 / $2.2 |
| Max output | - | - |
| Input | text, vision, audio | text |
| Released | 2026-07-30 | 2026-06-04 |
Respan Index by category
Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.
| Category | Inkling-Small | NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4 |
|---|---|---|
| Coding | 6.7 Inkling-Small | 6.7 NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4 |
| Agents | 41.2 Inkling-Small | 33.6 NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4 |
| Reasoning | 31.7 Inkling-Small | 31.5 NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4 |
| Knowledge & language | 19.1 Inkling-Small | 35.3 NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4 |
| Human preference | 50.6 Inkling-Small | 49.0 NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4 |
Benchmarks both report
Inkling-Small leads on 5 of the 8 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | Inkling-Small | NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4 |
|---|---|---|
| LMArena Agent (LMArena) | -0.1701 | -0.1576 |
| LMArena Elo | 1406 | 1427 |
| Chess Puzzles (Epoch AI) | 18% | 12% |
| GPQA Diamond | 88.5% | 87.9% |
| Mystery Game Puzzles (Epoch AI) | 6% | 20% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 90% | 86.7% |
| SWE-bench Verified | 80.2% | 69.7% |
| Toolathlon-Verified (HKUST) | 54.4% | 34.3% |
FAQ
Is Inkling-Small better than NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4?
Inkling-Small scores 29.4 on the Respan Index (#84), ahead of NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4 at 28.8 (#86). Inkling-Small leads on 5 of the 8 benchmarks both report.
Which is cheaper, Inkling-Small or NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4?
Inkling-Small lists at $0.45 input and $1.2 output per 1M tokens; NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4 at $0.5 and $2.2. Inkling-Small is 1.5x cheaper per token at list price.
Which has the larger context window?
Both accept 1M tokens of context.
Compare other models
- vsClaude Opus 4.8 vs NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4
- vsNVIDIA Nemotron 3 Ultra 550B-A55B NVFP4 vs NVIDIA Nemotron 3.5 Lightning 30B-A3B NVFP4
- vsInkling-Small vs GPT-5.2-Codex
- vsInkling-Small vs Kimi K2.5
- vsInkling-Small vs Qwen3.5 397B-A17B
- vsNVIDIA Nemotron 3 Ultra 550B-A55B NVFP4 vs Kimi K2.5
- vsNVIDIA Nemotron 3 Ultra 550B-A55B NVFP4 vs Hy3 preview
- vsNVIDIA Nemotron 3 Ultra 550B-A55B NVFP4 vs GLM-5