Across 20 comparable benchmarks, Inkling 2 Mini has better reported results on 20 and worse on 0. 2 further shared results are listed below, each with the reason it is not counted.
Strong evidence20 of 22 shared results countedHow we compare
Price basis: Standard rates. The price section below shows the applicable periods.
| Fact | Nemotron 3.5 Super VL | Inkling 2 Mini |
|---|---|---|
| Context window | 1M tokens | 1M tokens |
| Input / 1M | $0.150 | $0.150 |
| Output / 1M | $0.500 | $0.500 |
| Blended (4:1) | $0.126 | $0.123 |
| Status | Available | Available |
| Released | October 15, 2026 | November 20, 2026 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Mean of 13 shared benchmarks grouped by capability on a 0–100 scale. How averages are built
Inkling 2 Mini ahead on 3 of 3 counted
Inkling 2 Mini ahead on 1 of 1 counted
Inkling 2 Mini ahead on 2 of 2 counted
Inkling 2 Mini ahead on 2 of 2 counted
Inkling 2 Mini ahead on 2 of 2 counted
Inkling 2 Mini ahead on 6 of 6 counted
Inkling 2 Mini ahead on 1 of 1 counted
No fixed-scale average — see the rows in Benchmark results
No shared comparable results for Mathematics, Science & health, Cybersecurity.
Published scores, with matching modes where available. Gaps show Nemotron 3.5 Super VL relative to Inkling 2 Mini. Reading the results
| Benchmark | Nemotron 3.5 Super VL | Inkling 2 Mini | Gap |
|---|---|---|---|
| DeepSWERepository Engineering · Pass@1 (DeepSWE v1.1) | 24.6Unspecified Reasoning · tools | 48.2≠Thinking · tools | −23.6 pts#69 vs #61 of 73 |
| FrontierCode 2.0Repository Engineering · Weighted rubric score | 6.1Thinking · tools | 15.1Thinking · tools | 0.40×#32 vs #26 of 36 |
| Vibe Code Bench v1.1Code Generation & Editing · Pass rate (%) | 3.5Thinking · tools | 77.9Thinking · tools | −74.4 pts#111 vs #38 of 121 |
| ARC-AGI-1Abstract Generalization · Score (%) | 22.7Thinking High · no tools | 84.5≠Thinking · no tools | −61.8 pts#75 vs #47 of 87 |
| ARC-AGI-2Abstract Generalization · Score (% solved); cost per task (USD)Not counted · Speed and cost telemetry is reported, not scored | 1.9Thinking Medium · no tools | 49.3≠Thinking · no tools | 0.04×#75 vs #45 of 80 |
| MCP-AtlasTool Orchestration · Pass rate / claim coverage | 67.7Thinking · tools | 82.7Thinking · tools | −15.0 pts#41 vs #14 of 55 |
| ScreenSpot-Pro (no tools)GUI Grounding · Success rate (%) | 43.5Thinking · no tools | 76.5Thinking · no tools | −33.0 pts#7 vs #4 of 8 |
| BrowseCompFact Finding · Accuracy | 78.0Unspecified Reasoning · tools | 79.0≠Thinking · tools | −1.0 pts#26 vs #24 of 61 |
| DeepSearchQAFact Finding · F1 score | 77.7Thinking · tools | 85.3Thinking · tools | 0.91×#7 vs #4 of 9 |
| LongBench v2Long Reasoning · Accuracy | 62.1Thinking · no tools | 66.9Thinking · no tools | −4.8 pts#7 vs #2 of 22 |
| OpenAI MRCR v2 (8-needle, 256K–512K)Long Retrieval · Accuracy (%) | 5.7Thinking · no tools | 46.4Thinking · no tools | −40.7 pts#5 vs #3 of 5 |
| ChartographyDocuments & Charts · Score | 29.3Thinking · tools | 72.5Thinking · tools | 0.40×#26 vs #16 of 29 |
| GDP.pdfDocuments & Charts · Task pass rate (%) | 8.0Thinking · no tools | 16.8Thinking · no tools | −8.8 pts#66 vs #38 of 96 |
| MMMU-ProVisual Understanding · Accuracy | 72.3Thinking · no tools | 74.9Thinking · no tools | −2.6 pts#81 vs #69 of 136 |
| OmniDocBenchDocuments & Charts · Accuracy | 77.9Thinking · no tools | 92.8Thinking · no tools | −14.9 pts#5 vs #1 of 6 |
| PerceptionBenchVisual Understanding · Accuracy | 36.8Thinking · no tools | 57.5Thinking · no tools | −20.7 pts#19 vs #11 of 19 |
| ZeroBench MainVisual Understanding · Pass@1 / Pass@5 / Pass^5 | 12.0Thinking · tools | 34.0Thinking · tools | −22.0 pts#19 vs #16 of 21 |
| GDPval-AA v2Cross-industry Work · Elo score | 1211Unspecified Reasoning · tools | 1319≠Thinking · tools | 0.92×#20 vs #19 of 23 |
| JobBenchCross-industry Work · Mean task reward (%)Not counted · This metric has no better direction | 36.5Thinking · tools | 49.6Thinking · tools | — |
| HLE-DiamondKnowledge Exams · Accuracy (%) | 8.8Thinking · no tools | 15.2Thinking · no tools | −6.4 pts#15 vs #13 of 16 |
| AA Intelligence Index v5.0.1Capability Indices · Index (0-100) | 13.6Thinking High · tools | 20.1≠Thinking · no tools | 0.68×#49 vs #44 of 62 |
| Vals Index v2.2Capability Indices · GDP-weighted accuracy (%) | 29.8Thinking · tools | 46.5Thinking · tools | −16.7 pts#34 vs #31 of 36 |
Repository Engineering · Pass@1 (DeepSWE v1.1)
Repository Engineering · Weighted rubric score
Code Generation & Editing · Pass rate (%)
Tool Orchestration · Pass rate / claim coverage
GUI Grounding · Success rate (%)
Fact Finding · Accuracy
Fact Finding · F1 score
Long Reasoning · Accuracy
Long Retrieval · Accuracy (%)
Documents & Charts · Score
Documents & Charts · Task pass rate (%)
Visual Understanding · Accuracy
Documents & Charts · Accuracy
Visual Understanding · Accuracy
Visual Understanding · Pass@1 / Pass@5 / Pass^5
Cross-industry Work · Elo score
Cross-industry Work · Mean task reward (%)
Not counted · This metric has no better direction
Knowledge Exams · Accuracy (%)
Capability Indices · Index (0-100)
Capability Indices · GDP-weighted accuracy (%)
A dash means no result is available.
| Benchmark | Nemotron 3.5 Super VL | Inkling 2 Mini |
|---|---|---|
| CritPt | 10.9 | — |
| GPQA Diamond | 89.5 | — |
| HLE | 31.8 | — |
| SWE-bench Multilingual | 67.7 | — |
| SWE-bench Verified | 71.1 | — |
| Terminal-Bench 2.1 | 60.7 | — |
| Terminal-Bench 4.0 | 0.0 | — |
| Terminal-Bench 4.1 | 0.3 | — |
| AutomationBench-AA | — | 41.8 |
| OSWorld-Verified | 51.1 | — |
| LiveBench 2.0 | 56.0 | — |
| AA-LCR | 68.6 | — |
| BabyVision | 29.6 | — |
| CharXiv RQ | 80.8 | — |
| MathVision | 78.2 | — |
| Video-MME v2 | 32.9 | — |
| AA-AnalystAgent | — | 46.3 |
| AA-Briefcase | — | 1263 |
| τ²-Bench - Telecom | 73.2 | — |
| τ³-Banking | 18.9 | — |
Time-of-day providers use peak-hour rates; fixed-price providers use standard rates. Off-peak discounts remain in the published details.
Drag the handle above the bar for cache hits, the one below it for the input : output mix · 5% steps
Blended price = effective input rate at 90% cache hits × 80% + output rate × 20%
Nemotron 3.5 Super VL costs2.9%morethan Inkling 2 Mini per million tokens.Using standard rates at this token mix.
Nemotron 3.5 Super VL: Standard pricing. DeepInfra official models API (nvidia/NVIDIA-Nemotron-3.5-Super-VL) verified 2026-11-13
Inkling 2 Mini: Standard pricing. Tinker 64K/256K training (1M sampling); fine-tuning billed separately ($0.75/1M for 64K, $1.50/1M for 256K).
| Price / 1M tokens | Nemotron 3.5 Super VL | Inkling 2 Mini | Ratio |
|---|---|---|---|
| Input | $0.15 | $0.15 | 1.00× |
| Output | $0.50 | $0.50 | 1.00× |
| Cached input | $0.02 | $0.015 | 1.33× |
| Cache write | — | — | — |
| Blended | $0.126 | $0.123 | 1.03× |
Estimates use the selected token mix. Cache writes, tool fees and long-context surcharges are excluded.
Reported cost per task, paired with the score from the same run. Settings and sources may differ; costs do not affect the verdict.
| Benchmark | Nemotron 3.5 Super VL | Inkling 2 Mini |
|---|---|---|
| AA Intelligence Index v5.0.1 | Not reported | |
| ARC-AGI-1 | Not reported | |
| ARC-AGI-2 | Not reported | |
| LiveBench 2.0 | $0.1577 / task Average · Overall score (equal-weight mean of 7 suite scores, 0-100): 56.0 Max (task-specific tools) | Not reported |
| Terminal-Bench 4.0 | $0.86 / task Average · Resolution rate (%): 0.0 Unspecified Reasoning (With Tools) · vals-mini-swe | Not reported |
| Terminal-Bench 4.1 | Not reported |
| Attribute | Nemotron 3.5 Super VL | Inkling 2 Mini |
|---|---|---|
| Availability | Available | Available |
| Provider | NVIDIA | Thinking Machines Lab |
| Model type | Multimodal model | Reasoning model |
| First release | October 15, 2026 | November 20, 2026 |
| Context window | 1M tokens | 1M tokens |
| Total parameters | 120B | 26.4B |
| Active parameters | 12B | 5.4B |
| Architecture | Mixture of Experts (MoE) | Mixture of Experts (MoE) |
| Documented capabilities | Reasoning, Multilingual, Tool use, Function calling, Computer use, OCR, Long context, Coding | Reasoning, Coding, Tool use, Long context |
| Knowledge cutoff | 2025-12 | — |
| Input modalities | Text, Image, Video | Text, Image |
| Output modalities | Text | Text |
| Weights | Open weights | Open weights |
| Licence | OpenMDW License Agreement 1.1 | Apache 2.0 |
| Commercial use | Commercial use allowed | Commercial use allowed |
These are reported-score comparisons, not controlled head-to-head tests.
What people found comparing these models, or using either one. Comments also appear on the models' own pages.
Used Nemotron 3.5 Super VL or Inkling 2 Mini? Sign in with Google to share what worked, what did not, and which API or setup you tested.
No community comments on either model yet.
Alternatives with the most benchmark overlap for this matchup.