Skip to main content
BenchLM

Kimi K2.5 vs Nemotron 3.5 Lightning 30B A3B NVFP4

Updated September 24, 2026. Rank says Kimi K2.5 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Share or export
Share on XLinkedInSocial cardCSVJSON

Decision reading

Kimi K2.5 has the higher public score, 52.96 versus 19.1, and the 90% score intervals do not overlap. 8 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A
Moonshot AI logo

Moonshot AI

52.96/100

Supported · Public rank #63

90% interval 44.8–61.1

Model B
NVIDIA logo

NVIDIA

19.1/100

Estimated · Public rank #186

90% interval 9.2–29.0

Shared results
8
Kimi K2.5 only
37
Nemotron 3.5 Lightning 30B A3B NVFP4 only
5
Like-for-like categories
0 / 8
Supported: Kimi K2.5 · Estimated: Nemotron 3.5 Lightning 30B A3B NVFP4How the comparison works

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.

  • 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

    Kimi K2.5 and Nemotron 3.5 Lightning 30B A3B NVFP4 are scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.

    Confidence: limited
  • Agentic work

    Tool use, computer use, and multi-step task completion

    Not enough matched evidence

    Kimi K2.5 and Nemotron 3.5 Lightning 30B A3B NVFP4 are scored on Estimated evidence for agentic, so the reading is 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

Which one for a specific job

Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.

The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.

38.9Kimi K2.511.4Nemotron 3.5 Lightning 30B A3B NVFP4

Directional only · BenchAlign v5.7

Kimi K2.5 scores higher, but at least one score rests on Estimated evidence or a different benchmark set. Directional only, no winner.

Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.

Same basis rules as the category table below

What is actually comparable

Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.

4 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.

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.

Bars run 0–100 on each benchmark’s normalized display scale

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign v5.7 lane for agentic, coding, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.

Agentic

Directional only
Kimi K2.5
36.1
Estimated · #52/105
Nemotron 3.5 Lightning 30B A3B NVFP4
7.3
Estimated · #104/105
Basis
BenchAlign v5.7 lane · 14 vs 4 public rows
Reading
Directional only

Coding

Directional only
Kimi K2.5
38.9
Estimated · #61/135
Nemotron 3.5 Lightning 30B A3B NVFP4
11.4
Estimated · #135/135
Basis
BenchAlign v5.7 lane · 8 vs 4 public rows
Reading
Directional only

Knowledge

Directional only
Kimi K2.5
47.8
Estimated · #65/158
Nemotron 3.5 Lightning 30B A3B NVFP4
20.7
Estimated · #154/158
Basis
BenchAlign v5.7 lane · 6 vs 4 public rows
Reading
Directional only

Instruction following

Directional only
Kimi K2.5
84.4
#41/124
Nemotron 3.5 Lightning 30B A3B NVFP4
68.5
#67/124
Basis
Provisional lane · 0 vs 1 weighted rows
Reading
Directional only

Reasoning

Not comparable
Kimi K2.5
55.1
Unranked · 3 rankable rows
Nemotron 3.5 Lightning 30B A3B NVFP4
55.9
Unranked · 1 rankable row
Basis
Provisional lane · 1 vs 0 weighted rows
Reading
Not comparable

Multimodal

Not comparable
Kimi K2.5
65.8
#25/50
Nemotron 3.5 Lightning 30B A3B NVFP4
Not ranked
Basis
Provisional lane · 1 vs 0 weighted rows
Reading
Not comparable

Multilingual

Not comparable
Kimi K2.5
38.2
#8/12
Nemotron 3.5 Lightning 30B A3B NVFP4
Not ranked
Basis
Provisional lane · 1 vs 0 weighted rows
Reading
Not comparable

Math

Not comparable
Kimi K2.5
62.1
#4/7
Nemotron 3.5 Lightning 30B A3B NVFP4
Not ranked
Basis
Provisional lane · 4 vs 0 weighted rows
Reading
Not comparable

Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.7) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.

Bars run 0–100Methodology

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.

Cached input falls back to the list input rate only where a cached rate is unpublished

Specification differences

Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.

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 card

Documented 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, 52.96 versus 19.1, 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.

Questions

Which is better, Kimi K2.5 or Nemotron 3.5 Lightning 30B A3B NVFP4?

Kimi K2.5 has the higher public score, 52.96 versus 19.1, 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?

Kimi K2.5 scores higher for coding on the public lane, 38.9 to 11.4. Kimi K2.5 and Nemotron 3.5 Lightning 30B A3B NVFP4 are scored on Estimated evidence for coding, so the reading is directional rather than like-for-like. BenchLM does not name a winner for coding from a directional reading; 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 scores higher for agentic tasks on the public lane, 36.1 to 7.3. Kimi K2.5 and Nemotron 3.5 Lightning 30B A3B NVFP4 are scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.

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.

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.
Model the full break-even

Benchmark evidence

The full public result ledger is available for audit without forcing a wide desktop table onto a phone.

Browse raw public benchmark evidence50 rows

Agentic

  • Terminal-Bench 2.0

    Kimi K2.550.8%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

  • BrowseComp

    Kimi K2.560.6%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP436.8%
    Source

    Kimi K2.5 leads this result

  • Claw-Eval

    Kimi K2.552.3%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

  • QwenClawBench

    Kimi K2.554.3%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

  • τ³-bench results

    Kimi K2.565.7%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP49.5%
    Source

    Kimi K2.5 leads this result

  • DeepSearchQA

    Kimi K2.577.1%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

  • DeepPlanning

    Kimi K2.514.4%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

  • Toolathlon

    Kimi K2.527.8%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

  • MCP Atlas

    Kimi K2.529.5%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

  • MCP-Tasks

    Kimi K2.559.1%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

  • WideResearch

    Kimi K2.572.7%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

  • Gert Labs

    Kimi K2.545.88%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

  • ResearchClawBench

    Kimi K2.514.0%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

  • JobBench

    Kimi K2.58.7%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

  • Terminal-Bench 2.1

    Kimi K2.5—
    Nemotron 3.5 Lightning 30B A3B NVFP423.5%
    Source

    Not directly comparable

  • PinchBench

    Kimi K2.5—
    Nemotron 3.5 Lightning 30B A3B NVFP483.4%
    Source

    Not directly comparable

Coding

  • SWE-bench Verified

    Kimi K2.576.8%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP452.8%
    Source

    Kimi K2.5 leads this result

  • SWE-bench Verified*

    Kimi K2.570.8%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

  • LiveCodeBench v6

    Kimi K2.585.0%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

  • SWE-bench Pro

    Kimi K2.550.7%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

  • SWE Multilingual

    Kimi K2.573%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP436.5%
    Source

    Kimi K2.5 leads this result

  • SWE-Rebench

    Kimi K2.558.5%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

  • React Native Evals

    Kimi K2.577.2%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

  • SciCode

    Kimi K2.548.7%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP431.4%
    Source

    Kimi K2.5 leads this result

  • Terminal-Bench 2.1

    Kimi K2.5—
    Nemotron 3.5 Lightning 30B A3B NVFP423.5%
    Source

    Not directly comparable

Reasoning

  • LongBench v2

    Kimi K2.561%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

Multimodal

  • MMMU-Pro

    Kimi K2.578.5%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

  • Video-MME

    Kimi K2.587.4%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

  • MMVU

    Kimi K2.580.4%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

  • VideoMMMU

    Kimi K2.586.6%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

Knowledge

  • GPQA

    Kimi K2.587.6%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP475.6%
    Source

    Kimi K2.5 leads this result

  • GPQA-D

    Kimi K2.587.6%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP475.6%
    Source

    Kimi K2.5 leads this result

  • SuperGPQA

    Kimi K2.569.2%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

  • MMLU-Pro

    Kimi K2.587.1%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP481.6%
    Source

    Kimi K2.5 leads this result

  • MMLU-Pro (Arcee)

    Kimi K2.587.1%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

  • HLE

    Kimi K2.530.1%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

  • HLE w/o tools

    Kimi K2.5—
    Nemotron 3.5 Lightning 30B A3B NVFP410.5%
    Source

    Not directly comparable

Multilingual

  • MMLU-ProX

    Kimi K2.582.3%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

  • NOVA-63

    Kimi K2.556.0%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

Instruction following

  • IFEval

    Kimi K2.593.9%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

  • IFBench

    Kimi K2.5—
    Nemotron 3.5 Lightning 30B A3B NVFP472.9%
    Source

    Not directly comparable

Math

  • AIME 2025

    Kimi K2.596.1%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

  • AIME26

    Kimi K2.595.8%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

  • AIME25 (Arcee)

    Kimi K2.596.3%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

  • HMMT Feb 2025

    Kimi K2.595.4%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

  • HMMT Nov 2025

    Kimi K2.591.1%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

  • HMMT Feb 2026

    Kimi K2.587.1%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

  • MMAnswerBench

    Kimi K2.581.8%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

  • FrontierMath v2 (Tiers 1-3)

    Kimi K2.527.900%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

  • FrontierMath v2 (Tier 4)

    Kimi K2.54.200%
    Source
    Nemotron 3.5 Lightning 30B A3B NVFP4—

    Not directly comparable

50 public results · 8 shared

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 issue

Join 2,000+ readers.

Last updated September 24, 2026