Long documents
Prompts that approach the documented context limit
Ling 3.0 Flash
Ling 3.0 Flash has the larger documented context window.
Confidence: documented
LFM2.5-24B-A2B vs Ling 3.0 Flash
Updated October 13, 2026. Rank says Ling 3.0 Flash is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
Both of these models will change. Get the price, version and retirement notices for the pair, each with its source. Follow model changes
Share or export
Decision reading
Ling 3.0 Flash has the higher public point estimate, 45.04 versus 37.8. Their conditional score ranges overlap. These ranges do not establish rank confidence. 6 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
- Shared results
- 6
- LFM2.5-24B-A2B only
- 7
- Ling 3.0 Flash only
- 16
- Like-for-like categories
- 1 / 8
Estimated: LFM2.5-24B-A2B and Ling 3.0 Flash. Conditional ranges do not establish rank confidence.How 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.
Show secondary and unsupported calls
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
LFM2.5-24B-A2B is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.
Confidence: limitedAgentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
LFM2.5-24B-A2B is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
Confidence: limitedChat 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-ratesCache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. LFM2.5-24B-A2B does not fit this workload in one request. Ling 3.0 Flash has no comparable published API token rate.
Confidence: listed-ratesRepository 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.
28.5LFM2.5-24B-A2B32.3Ling 3.0 Flash
Directional only · BenchAlign v5.8
Ling 3.0 Flash has the higher coding point estimate. Conditional score ranges do not establish rank confidence.
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.
7 LFM2.5-24B-A2B only
6 Shared
16 Ling 3.0 Flash only
3 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.
HLEKnowledge
Normalized gap 15.3LFM2.5-24B-A2B:7.4%Ling 3.0 Flash:22.7%GPQAKnowledge
Normalized gap 10.5LFM2.5-24B-A2B:74.4%Ling 3.0 Flash:85.0%SciCodeCoding
Normalized gap 8.5LFM2.5-24B-A2B:32.7%Ling 3.0 Flash:41.2%IFBenchInstruction following
Normalized gap 0.2LFM2.5-24B-A2B:74.7%Ling 3.0 Flash:74.5%
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 v5.8 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.
Instruction following
Like-for-like- LFM2.5-24B-A2B
- 75.6
- #61/128
- Ling 3.0 Flash
- 75.2
- #64/128
- Basis
- Provisional lane · 1 vs 1 weighted rows
- Reading
- Practical tie
Agentic
Directional only- LFM2.5-24B-A2B
- 30.2
- Estimated · #88/124
- Ling 3.0 Flash
- 32.5
- Supported · #81/124
- Basis
- BenchAlign v5.8 lane · 5 vs 7 public rows
- Reading
- Directional only
Coding
Directional only- LFM2.5-24B-A2B
- 28.5
- Estimated · #98/149
- Ling 3.0 Flash
- 32.3
- Supported · #87/149
- Basis
- BenchAlign v5.8 lane · 2 vs 6 public rows
- Reading
- Directional only
Knowledge
Directional only- LFM2.5-24B-A2B
- 40.8
- Estimated · #112/181
- Ling 3.0 Flash
- 43.6
- Supported · #103/181
- Basis
- BenchAlign v5.8 lane · 3 vs 5 public rows
- Reading
- Directional only
Reasoning
Not comparable- LFM2.5-24B-A2B
- Not ranked
- Ling 3.0 Flash
- 76.0
- Unranked · 2 rankable rows
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- LFM2.5-24B-A2B
- Not ranked
- Ling 3.0 Flash
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- LFM2.5-24B-A2B
- Not ranked
- Ling 3.0 Flash
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- LFM2.5-24B-A2B
- Not ranked
- Ling 3.0 Flash
- 81.1
- Unranked · 3 rankable rows
- Basis
- Provisional lane · 0 vs 2 weighted rows
- Reading
- Not comparable
| Category | LFM2.5-24B-A2B | Ling 3.0 Flash | Basis | Reading |
|---|---|---|---|---|
| Instruction following | 75.6#61/128 | 75.2#64/128 | Like-for-likeProvisional lane · 1 vs 1 weighted rows | Practical tie |
| Agentic | 30.2Estimated · #88/124 | 32.5Supported · #81/124 | Directional onlyBenchAlign v5.8 lane · 5 vs 7 public rows | Directional only |
| Coding | 28.5Estimated · #98/149 | 32.3Supported · #87/149 | Directional onlyBenchAlign v5.8 lane · 2 vs 6 public rows | Directional only |
| Knowledge | 40.8Estimated · #112/181 | 43.6Supported · #103/181 | Directional onlyBenchAlign v5.8 lane · 3 vs 5 public rows | Directional only |
| Reasoning | Not ranked | 76.0Unranked · 2 rankable rows | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multimodal | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | Not ranked | 81.1Unranked · 3 rankable rows | Not comparableProvisional lane · 0 vs 2 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.8) 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.
Supported evidence per lane · 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
- LFM2.5-24B-A2B
- $0.0006
- Fits in one request
- Ling 3.0 Flash
- API rate not published
- Fits in one request
Ling 3.0 Flash has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- LFM2.5-24B-A2B
- $0.008
- Fits in one request
- Ling 3.0 Flash
- API rate not published
- Fits in one request
Ling 3.0 Flash has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- LFM2.5-24B-A2B
- $0.022
- Does not fit in one request
- Ling 3.0 Flash
- API rate not published
- Fits in one request
- Cached-input rate unavailable
LFM2.5-24B-A2B does not fit this workload in one request. Ling 3.0 Flash 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.
SpecificationLFM2.5-24B-A2BLing 3.0 Flash
Context window
Maximum documented context; output-token limits may be lower.
LFM2.5-24B-A2B
Ling 3.0 Flash
API model ID
LFM2.5-24B-A2B
Not sourced
Ling 3.0 Flash
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
LFM2.5-24B-A2B
$0.05 per 1M cached input tokens
Liquid AI launch postLing 3.0 Flash
No comparable hosted API rate
InclusionAI Ling 3.0 Flash model cardDocumented inputs
LFM2.5-24B-A2B
Not sourced
Ling 3.0 Flash
Not sourced
Documented outputs
LFM2.5-24B-A2B
Not sourced
Ling 3.0 Flash
Not sourced
Provider availability
LFM2.5-24B-A2B
Not sourced
Ling 3.0 Flash
Not sourced
Reasoning profile
LFM2.5-24B-A2B
Reasoning
Ling 3.0 Flash
Reasoning
Weight access
LFM2.5-24B-A2B
Open Weight
Ling 3.0 Flash
Open Weight
License
LFM2.5-24B-A2B
Open Weight
Ling 3.0 Flash
Open Weight
Release date
LFM2.5-24B-A2B
2026-10-13
Ling 3.0 Flash
2026-07-23
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
- Ling 3.0 Flash has the higher public point estimate, 45.04 versus 37.8. Their conditional score ranges overlap. These ranges do not establish rank confidence.
- Workload cost
- A complete comparable API-rate estimate is not available for both models.
- Context tradeoff
- Ling 3.0 Flash has the larger documented window (262K).
Run the same representative tasks against both endpoints before changing production traffic.
Questions
Which is better, LFM2.5-24B-A2B or Ling 3.0 Flash?
Ling 3.0 Flash has the higher public point estimate, 45.04 versus 37.8. Their conditional score ranges overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.
Which is better for coding, LFM2.5-24B-A2B or Ling 3.0 Flash?
Ling 3.0 Flash scores higher for coding on the public lane, 32.3 to 28.5. LFM2.5-24B-A2B is 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, LFM2.5-24B-A2B or Ling 3.0 Flash?
Ling 3.0 Flash scores higher for agentic tasks on the public lane, 32.5 to 30.2. LFM2.5-24B-A2B is 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, LFM2.5-24B-A2B or Ling 3.0 Flash?
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, LFM2.5-24B-A2B or Ling 3.0 Flash?
Ling 3.0 Flash has the larger documented context window: 262K, compared with 131K.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence29 rows
Agentic
AutomationBench
LFM2.5-24B-A2B27.7%SourceLing 3.0 Flash—Not directly comparable
BFCL v4
LFM2.5-24B-A2B65.0%SourceLing 3.0 Flash73.0%SourceLing 3.0 Flash leads this result
τ³-bench results
LFM2.5-24B-A2B8.0%SourceLing 3.0 Flash—Not directly comparable
PinchBench
LFM2.5-24B-A2B83.2%SourceLing 3.0 Flash—Not directly comparable
WebArena-Verified
LFM2.5-24B-A2B26.8%SourceLing 3.0 Flash—Not directly comparable
MCP Atlas
LFM2.5-24B-A2B—Ling 3.0 Flash65.5%SourceNot directly comparable
skillsBench
LFM2.5-24B-A2B—Ling 3.0 Flash44.8%SourceNot directly comparable
WideResearch
LFM2.5-24B-A2B—Ling 3.0 Flash73.6%SourceNot directly comparable
BrowseComp
LFM2.5-24B-A2B—Ling 3.0 Flash72.2%SourceNot directly comparable
DRACO
LFM2.5-24B-A2B—Ling 3.0 Flash70.4%SourceNot directly comparable
Terminal-Bench 2.1 (Vals)
LFM2.5-24B-A2B—Ling 3.0 Flash50.2%SourceNot directly comparable
Coding
SciCode
LFM2.5-24B-A2B32.7%SourceLing 3.0 Flash41.2%SourceLing 3.0 Flash leads this result
SWE-bench Verified
LFM2.5-24B-A2B51%SourceLing 3.0 Flash—Not directly comparable
SWE-bench Pro
LFM2.5-24B-A2B—Ling 3.0 Flash56.6%SourceNot directly comparable
SWE Multilingual
LFM2.5-24B-A2B—Ling 3.0 Flash72.4%SourceNot directly comparable
LiveCodeBench v5
LFM2.5-24B-A2B—Ling 3.0 Flash82.8%SourceNot directly comparable
LiveCodeBench (Vals)
LFM2.5-24B-A2B—Ling 3.0 Flash84.0%SourceNot directly comparable
SWE-bench (Vals)
LFM2.5-24B-A2B—Ling 3.0 Flash65.2%SourceNot directly comparable
Knowledge
GPQA
LFM2.5-24B-A2B74.4%SourceLing 3.0 Flash85.0%SourceLing 3.0 Flash leads this result
GPQA-D
LFM2.5-24B-A2B74.4%SourceLing 3.0 Flash85.0%SourceLing 3.0 Flash leads this result
HLE
LFM2.5-24B-A2B7.4%SourceLing 3.0 Flash22.7%SourceLing 3.0 Flash leads this result
GPQA Diamond (Vals)
LFM2.5-24B-A2B—Ling 3.0 Flash84.8%SourceNot directly comparable
MMLU-Pro (Vals)
LFM2.5-24B-A2B—Ling 3.0 Flash82.0%SourceNot directly comparable
Instruction following
Math
29 public results · 6 shared
Watch LFM2.5-24B-A2B vs Ling 3.0 Flash
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 5,500+ readers.
Last updated October 13, 2026