Agentic
Like-for-like- Kimi K2.5
- 55.0
- Nemotron 3.5 Lightning 30B A3B NVFP4
- 29.1
- Weighted basis
- 2 vs 2 rows
- Reading
- Kimi K2.5 leads
Model comparison
Kimi K2.5 vs Nemotron 3.5 Lightning 30B A3B NVFP4
Updated August 11, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Nemotron 3.5 Lightning 30B A3B NVFP4
NVIDIA
26.9/100
Estimated · Public rank #204
90% interval 17.1–36.8
Kimi K2.5 has the higher public score, 58.8 versus 26.93, and the 90% score intervals do not overlap.
9 results are shared. Category rows based on different benchmark sets are marked directional and do not name a winner.
Which one for your work
Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.
Agentic work
Tool use, computer use, and multi-step task completion
Kimi K2.5
Kimi K2.5 leads on the same 2 weighted benchmark rows.
Confidence: limited
Long documents
Prompts that approach the documented context limit
Nemotron 3.5 Lightning 30B A3B NVFP4
Nemotron 3.5 Lightning 30B A3B NVFP4 has the larger documented context window.
Confidence: documented
Show secondary and unsupported calls
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
The category averages use different weighted benchmark sets, so they are directional rather than like-for-like.
Confidence: limited
Chat turn cost
1K fresh input + 500 output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: rate-fallback
Repository review cost
50K fresh input + 3K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
36 Kimi K2.5 only
9 Shared
4 Nemotron 3.5 Lightning 30B A3B NVFP4 only
- Shared results
- 9
- Kimi K2.5 only
- 36
- Nemotron 3.5 Lightning 30B A3B NVFP4 only
- 4
- Like-for-like categories
- 1 / 8
2 categories use different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Category results, on a stated basis
Each row states whether both averages use the same weighted benchmark set. Directional and not-comparable rows remain visible, but they never receive a winner in this template.
Coding
Directional only- Kimi K2.5
- 59.4
- Nemotron 3.5 Lightning 30B A3B NVFP4
- 42.1
- Weighted basis
- 4 vs 2 rows
- Reading
- Directional only
Knowledge
Directional only- Kimi K2.5
- 56.9
- Nemotron 3.5 Lightning 30B A3B NVFP4
- 80.5
- Weighted basis
- 4 vs 2 rows
- Reading
- Directional only
Reasoning
Not comparable- Kimi K2.5
- 61.0
- Nemotron 3.5 Lightning 30B A3B NVFP4
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
Math
Not comparable- Kimi K2.5
- 60.6
- Nemotron 3.5 Lightning 30B A3B NVFP4
- Not measured
- Weighted basis
- 4 vs 0 rows
- Reading
- Not comparable
Multilingual
Not comparable- Kimi K2.5
- 82.3
- Nemotron 3.5 Lightning 30B A3B NVFP4
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
Multimodal
Not comparable- Kimi K2.5
- 78.5
- Nemotron 3.5 Lightning 30B A3B NVFP4
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
Instruction following
Not comparable- Kimi K2.5
- 93.9
- Nemotron 3.5 Lightning 30B A3B NVFP4
- 72.9
- Weighted basis
- 1 vs 1 rows
- Reading
- Not comparable
| Category | Kimi K2.5 | Nemotron 3.5 Lightning 30B A3B NVFP4 | Weighted basis | Reading |
|---|---|---|---|---|
| Agentic | 55.0 | 29.1 | Like-for-like2 vs 2 rows | Kimi K2.5 leads |
| Coding | 59.4 | 42.1 | Directional only4 vs 2 rows | Directional only |
| Knowledge | 56.9 | 80.5 | Directional only4 vs 2 rows | Directional only |
| Reasoning | 61.0 | Not measured | Not comparable1 vs 0 rows | Not comparable |
| Math | 60.6 | Not measured | Not comparable4 vs 0 rows | Not comparable |
| Multilingual | 82.3 | Not measured | Not comparable1 vs 0 rows | Not comparable |
| Multimodal | 78.5 | Not measured | Not comparable1 vs 0 rows | Not comparable |
| Instruction following | 93.9 | 72.9 | Not comparable1 vs 1 rows | Not comparable |
Shape of the matched evidence
Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.
Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.
Terminal-Bench 2.0
Agentic
Kimi K2.5: 50.8%Nemotron 3.5 Lightning 30B A3B NVFP4: 23.5%Normalized gap 27.3Kimi K2.5 source Nemotron 3.5 Lightning 30B A3B NVFP4 sourceSWE-bench Verified
Coding
Kimi K2.5: 76.8%Nemotron 3.5 Lightning 30B A3B NVFP4: 52.8%Normalized gap 24.0Kimi K2.5 source Nemotron 3.5 Lightning 30B A3B NVFP4 sourceBrowseComp
Agentic
Kimi K2.5: 60.6%Nemotron 3.5 Lightning 30B A3B NVFP4: 36.8%Normalized gap 23.8Kimi K2.5 source Nemotron 3.5 Lightning 30B A3B NVFP4 sourceSciCode
Coding
Kimi K2.5: 48.7%Nemotron 3.5 Lightning 30B A3B NVFP4: 31.4%Normalized gap 17.3Kimi K2.5 source Nemotron 3.5 Lightning 30B A3B NVFP4 sourceGPQA
Knowledge
Kimi K2.5: 87.6%Nemotron 3.5 Lightning 30B A3B NVFP4: 75.6%Normalized gap 12.0Kimi K2.5 source Nemotron 3.5 Lightning 30B A3B NVFP4 source
What each workload costs
Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.
Chat turn
1K fresh input + 500 output tokens
- Kimi K2.5
- $0.0021
- Fits in one request
- Nemotron 3.5 Lightning 30B A3B NVFP4
- Self-hosted; infrastructure cost varies
- Fits in one request
Nemotron 3.5 Lightning 30B A3B NVFP4 has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- Kimi K2.5
- $0.039
- Fits in one request
- Nemotron 3.5 Lightning 30B A3B NVFP4
- Self-hosted; infrastructure cost varies
- Fits in one request
Nemotron 3.5 Lightning 30B A3B NVFP4 has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Kimi K2.5
- $0.162
- Fits in one request
- Cached input priced at the published list-input rate
- Nemotron 3.5 Lightning 30B A3B NVFP4
- Self-hosted; infrastructure cost varies
- Fits in one request
- Cached-input rate unavailable
Kimi K2.5 has no published cached-input rate, so cached tokens use its listed input rate. Nemotron 3.5 Lightning 30B A3B NVFP4 has no comparable published API token rate.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationKimi K2.5Nemotron 3.5 Lightning 30B A3B NVFP4
Context window
Maximum documented context; output-token limits may be lower.
Kimi K2.5
256K
Nemotron 3.5 Lightning 30B A3B NVFP4
API model ID
Kimi K2.5
Not sourced
Nemotron 3.5 Lightning 30B A3B NVFP4
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Kimi K2.5
Not published
Nemotron 3.5 Lightning 30B A3B NVFP4
No comparable hosted API rate
NVIDIA Nemotron 3.5 Lightning model cardDocumented inputs
Kimi K2.5
Not sourced
Nemotron 3.5 Lightning 30B A3B NVFP4
Not sourced
Documented outputs
Kimi K2.5
Not sourced
Nemotron 3.5 Lightning 30B A3B NVFP4
Not sourced
Provider availability
Kimi K2.5
Not sourced
Nemotron 3.5 Lightning 30B A3B NVFP4
Not sourced
Reasoning profile
Kimi K2.5
Non-Reasoning
Nemotron 3.5 Lightning 30B A3B NVFP4
Reasoning
Weight access
Kimi K2.5
Open Weight
Nemotron 3.5 Lightning 30B A3B NVFP4
Open Weight
License
Kimi K2.5
Open Weight
Nemotron 3.5 Lightning 30B A3B NVFP4
Open Weight
Release date
Kimi K2.5
2026-02-01
Nemotron 3.5 Lightning 30B A3B NVFP4
2026-08-11
If you already use one of these models
- Deployment change
- The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
- Quality signal
- Kimi K2.5 has the higher public score, 58.8 versus 26.93, and the 90% score intervals do not overlap.
- Workload cost
- A complete comparable API-rate estimate is not available for both models.
- Context tradeoff
- Nemotron 3.5 Lightning 30B A3B NVFP4 has the larger documented window (1M).
Run the same representative tasks against both endpoints before changing production traffic.
Self-host vs API cost
Estimates at 50,000 req/day · 1000 tokens/req average.
Kimi K2.5
API / mo$2,700
Self-host / mo$5,221
Break-even132M/day
Nemotron 3.5 Lightning 30B A3B NVFP4
API / mo$0
Self-host / moNot listed
Break-even—
Proprietary model — self-hosting not applicable.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence49 rows
Agentic
Terminal-Bench 2.0
Kimi K2.550.8%SourceNemotron 3.5 Lightning 30B A3B NVFP423.5%SourceKimi K2.5 leads this result
BrowseComp
Kimi K2.560.6%SourceNemotron 3.5 Lightning 30B A3B NVFP436.8%SourceKimi K2.5 leads this result
Claw-Eval
Kimi K2.552.3%SourceNemotron 3.5 Lightning 30B A3B NVFP4—Not directly comparable
QwenClawBench
Kimi K2.554.3%SourceNemotron 3.5 Lightning 30B A3B NVFP4—Not directly comparable
τ³-bench results
Kimi K2.565.7%SourceNemotron 3.5 Lightning 30B A3B NVFP49.5%SourceKimi K2.5 leads this result
DeepSearchQA
Kimi K2.577.1%SourceNemotron 3.5 Lightning 30B A3B NVFP4—Not directly comparable
DeepPlanning
Kimi K2.514.4%SourceNemotron 3.5 Lightning 30B A3B NVFP4—Not directly comparable
Toolathlon
Kimi K2.527.8%SourceNemotron 3.5 Lightning 30B A3B NVFP4—Not directly comparable
MCP Atlas
Kimi K2.529.5%SourceNemotron 3.5 Lightning 30B A3B NVFP4—Not directly comparable
MCP-Tasks
Kimi K2.559.1%SourceNemotron 3.5 Lightning 30B A3B NVFP4—Not directly comparable
WideResearch
Kimi K2.572.7%SourceNemotron 3.5 Lightning 30B A3B NVFP4—Not directly comparable
Gert Labs
Kimi K2.545.88%SourceNemotron 3.5 Lightning 30B A3B NVFP4—Not directly comparable
ResearchClawBench
Kimi K2.514.0%SourceNemotron 3.5 Lightning 30B A3B NVFP4—Not directly comparable
JobBench
Kimi K2.58.7%SourceNemotron 3.5 Lightning 30B A3B NVFP4—Not directly comparable
PinchBench
Kimi K2.5—Nemotron 3.5 Lightning 30B A3B NVFP483.4%SourceNot directly comparable
Coding
SWE-bench Verified
Kimi K2.576.8%SourceNemotron 3.5 Lightning 30B A3B NVFP452.8%SourceKimi K2.5 leads this result
SWE-bench Verified*
Kimi K2.570.8%SourceNemotron 3.5 Lightning 30B A3B NVFP4—Not directly comparable
LiveCodeBench v6
Kimi K2.585.0%SourceNemotron 3.5 Lightning 30B A3B NVFP4—Not directly comparable
SWE-bench Pro
Kimi K2.550.7%SourceNemotron 3.5 Lightning 30B A3B NVFP4—Not directly comparable
SWE Multilingual
Kimi K2.573%SourceNemotron 3.5 Lightning 30B A3B NVFP436.5%SourceKimi K2.5 leads this result
SWE-Rebench
Kimi K2.558.5%SourceNemotron 3.5 Lightning 30B A3B NVFP4—Not directly comparable
React Native Evals
Kimi K2.577.2%SourceNemotron 3.5 Lightning 30B A3B NVFP4—Not directly comparable
SciCode
Kimi K2.548.7%SourceNemotron 3.5 Lightning 30B A3B NVFP431.4%SourceKimi K2.5 leads this result
Terminal-Bench 2.0
Kimi K2.5—Nemotron 3.5 Lightning 30B A3B NVFP423.5%SourceNot directly comparable
Reasoning
LongBench v2
Kimi K2.561%SourceNemotron 3.5 Lightning 30B A3B NVFP4—Not directly comparable
Knowledge
GPQA
Kimi K2.587.6%SourceNemotron 3.5 Lightning 30B A3B NVFP475.6%SourceKimi K2.5 leads this result
GPQA-D
Kimi K2.587.6%SourceNemotron 3.5 Lightning 30B A3B NVFP475.6%SourceKimi K2.5 leads this result
SuperGPQA
Kimi K2.569.2%SourceNemotron 3.5 Lightning 30B A3B NVFP4—Not directly comparable
MMLU-Pro
Kimi K2.587.1%SourceNemotron 3.5 Lightning 30B A3B NVFP481.6%SourceKimi K2.5 leads this result
MMLU-Pro (Arcee)
Kimi K2.587.1%SourceNemotron 3.5 Lightning 30B A3B NVFP4—Not directly comparable
HLE
Kimi K2.530.1%SourceNemotron 3.5 Lightning 30B A3B NVFP4—Not directly comparable
HLE w/o tools
Kimi K2.5—Nemotron 3.5 Lightning 30B A3B NVFP410.5%SourceNot directly comparable
Math
AIME 2025
Kimi K2.596.1%SourceNemotron 3.5 Lightning 30B A3B NVFP4—Not directly comparable
AIME26
Kimi K2.595.8%SourceNemotron 3.5 Lightning 30B A3B NVFP4—Not directly comparable
AIME25 (Arcee)
Kimi K2.596.3%SourceNemotron 3.5 Lightning 30B A3B NVFP4—Not directly comparable
HMMT Feb 2025
Kimi K2.595.4%SourceNemotron 3.5 Lightning 30B A3B NVFP4—Not directly comparable
HMMT Nov 2025
Kimi K2.591.1%SourceNemotron 3.5 Lightning 30B A3B NVFP4—Not directly comparable
HMMT Feb 2026
Kimi K2.587.1%SourceNemotron 3.5 Lightning 30B A3B NVFP4—Not directly comparable
MMAnswerBench
Kimi K2.581.8%SourceNemotron 3.5 Lightning 30B A3B NVFP4—Not directly comparable
FrontierMath v2 (Tiers 1-3)
Kimi K2.527.900%SourceNemotron 3.5 Lightning 30B A3B NVFP4—Not directly comparable
FrontierMath v2 (Tier 4)
Kimi K2.54.200%SourceNemotron 3.5 Lightning 30B A3B NVFP4—Not directly comparable
Multilingual
Multimodal
MMMU-Pro
Kimi K2.578.5%SourceNemotron 3.5 Lightning 30B A3B NVFP4—Not directly comparable
Video-MME
Kimi K2.587.4%SourceNemotron 3.5 Lightning 30B A3B NVFP4—Not directly comparable
MMVU
Kimi K2.580.4%SourceNemotron 3.5 Lightning 30B A3B NVFP4—Not directly comparable
VideoMMMU
Kimi K2.586.6%SourceNemotron 3.5 Lightning 30B A3B NVFP4—Not directly comparable
Instruction following
Frequently asked questions
Which is better, Kimi K2.5 or Nemotron 3.5 Lightning 30B A3B NVFP4?
Kimi K2.5 has the higher public score, 58.8 versus 26.93, and the 90% score intervals do not overlap. That is the clearest overall quality signal in the current public data.
Which is better for coding, Kimi K2.5 or Nemotron 3.5 Lightning 30B A3B NVFP4?
The current coding averages use different weighted benchmark sets, so BenchLM does not name a winner from them. Read the shared benchmark rows directly and test the models on the same task set.
Which is better for agentic tasks, Kimi K2.5 or Nemotron 3.5 Lightning 30B A3B NVFP4?
Kimi K2.5 leads the like-for-like agentic tasks comparison across 2 shared weighted benchmark rows.
Which costs less, Kimi K2.5 or Nemotron 3.5 Lightning 30B A3B NVFP4?
Both models do not have comparable published API token rates, so this page does not name a universal price winner.
Which has the larger context window, Kimi K2.5 or Nemotron 3.5 Lightning 30B A3B NVFP4?
Nemotron 3.5 Lightning 30B A3B NVFP4 has the larger documented context window: 1M, compared with 256K.
Related comparisons
Last updated August 11, 2026
Watch Kimi K2.5 vs Nemotron 3.5 Lightning 30B A3B NVFP4
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.