Instruction following
Like-for-like- Ling 3.0 Flash
- 75.6
- #58/120
- MAI-Thinking-1
- 94.7
- #1/120
- Basis
- Provisional lane · 1 vs 1 weighted rows
- Reading
- MAI-Thinking-1 leads
Ling 3.0 Flash vs MAI-Thinking-1
Updated September 4, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
MAI-Thinking-1 has the higher public score estimate, 52.27 versus 52.2, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
6 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Share or export
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
Ling 3.0 Flash
Ling 3.0 Flash 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
Ling 3.0 Flash and MAI-Thinking-1 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
MAI-Thinking-1 is 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: listed-rates
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.
16 Ling 3.0 Flash only
6 Shared
8 MAI-Thinking-1 only
- Shared results
- 6
- Ling 3.0 Flash only
- 16
- MAI-Thinking-1 only
- 8
- Like-for-like categories
- 1 / 8
3 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Category results, on a stated basis
Each row shows the public-lane category score for both models: the BenchAlign 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- Ling 3.0 Flash
- 40.0
- Supported · #121/151
- MAI-Thinking-1
- 51.7
- Estimated · #53/151
- Basis
- BenchAlign lane · 7 vs 1 public rows
- Reading
- Directional only
Coding
Directional only- Ling 3.0 Flash
- 42.8
- Estimated · #126/183
- MAI-Thinking-1
- 51.8
- Estimated · #60/183
- Basis
- BenchAlign lane · 6 vs 4 public rows
- Reading
- Directional only
Knowledge
Directional only- Ling 3.0 Flash
- 45.9
- Supported · #112/181
- MAI-Thinking-1
- 53.3
- Estimated · #68/181
- Basis
- BenchAlign lane · 5 vs 4 public rows
- Reading
- Directional only
Reasoning
Not comparable- Ling 3.0 Flash
- 69.2
- Unranked · 2 rankable rows
- MAI-Thinking-1
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- Ling 3.0 Flash
- 73.7
- Unranked · 3 rankable rows
- MAI-Thinking-1
- 73.4
- Unranked · 3 rankable rows
- Basis
- Provisional lane · 2 vs 2 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Ling 3.0 Flash
- Not ranked
- MAI-Thinking-1
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- Ling 3.0 Flash
- Not ranked
- MAI-Thinking-1
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | Ling 3.0 Flash | MAI-Thinking-1 | Basis | Reading |
|---|---|---|---|---|
| Instruction following | 75.6#58/120 | 94.7#1/120 | Like-for-likeProvisional lane · 1 vs 1 weighted rows | MAI-Thinking-1 leads |
| Agentic | 40.0Supported · #121/151 | 51.7Estimated · #53/151 | Directional onlyBenchAlign lane · 7 vs 1 public rows | Directional only |
| Coding | 42.8Estimated · #126/183 | 51.8Estimated · #60/183 | Directional onlyBenchAlign lane · 6 vs 4 public rows | Directional only |
| Knowledge | 45.9Supported · #112/181 | 53.3Estimated · #68/181 | Directional onlyBenchAlign lane · 5 vs 4 public rows | Directional only |
| Reasoning | 69.2Unranked · 2 rankable rows | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | 73.7Unranked · 3 rankable rows | 73.4Unranked · 3 rankable rows | Not comparableProvisional lane · 2 vs 2 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | 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 |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign) differ from the provisional-lane categories. Unranked scores sit on the lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
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.
IFBench
Instruction following
Ling 3.0 Flash: 74.5%MAI-Thinking-1: 85%Normalized gap 10.5Ling 3.0 Flash source MAI-Thinking-1 sourceSWE-bench Pro
Coding
Ling 3.0 Flash: 56.6%MAI-Thinking-1: 52.8%Normalized gap 3.8Ling 3.0 Flash source MAI-Thinking-1 sourceHMMT Feb 2026
Math
Ling 3.0 Flash: 87.0%MAI-Thinking-1: 84.9%Normalized gap 2.1Ling 3.0 Flash source MAI-Thinking-1 sourceAIME26
Math
Ling 3.0 Flash: 93.2%MAI-Thinking-1: 94.5%Normalized gap 1.3Ling 3.0 Flash source MAI-Thinking-1 sourceGPQA
Knowledge
Ling 3.0 Flash: 85.0%MAI-Thinking-1: 84.2%Normalized gap 0.8Ling 3.0 Flash source MAI-Thinking-1 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
- Ling 3.0 Flash
- API rate not published
- Fits in one request
- MAI-Thinking-1
- API rate not published
- Fits in one request
Ling 3.0 Flash has no comparable published API token rate. MAI-Thinking-1 has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- Ling 3.0 Flash
- API rate not published
- Fits in one request
- MAI-Thinking-1
- API rate not published
- Fits in one request
Ling 3.0 Flash has no comparable published API token rate. MAI-Thinking-1 has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Ling 3.0 Flash
- API rate not published
- Fits in one request
- Cached-input rate unavailable
- MAI-Thinking-1
- API rate not published
- Fits in one request
- Cached-input rate unavailable
Ling 3.0 Flash has no comparable published API token rate. MAI-Thinking-1 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.
SpecificationLing 3.0 FlashMAI-Thinking-1
Context window
Maximum documented context; output-token limits may be lower.
Ling 3.0 Flash
MAI-Thinking-1
256K
API model ID
Ling 3.0 Flash
Not sourced
MAI-Thinking-1
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Ling 3.0 Flash
No comparable hosted API rate
InclusionAI Ling 3.0 Flash model cardMAI-Thinking-1
No comparable hosted API rate
Documented inputs
Ling 3.0 Flash
Not sourced
MAI-Thinking-1
Not sourced
Documented outputs
Ling 3.0 Flash
Not sourced
MAI-Thinking-1
Not sourced
Provider availability
Ling 3.0 Flash
Not sourced
MAI-Thinking-1
Not sourced
Reasoning profile
Ling 3.0 Flash
Reasoning
MAI-Thinking-1
Reasoning
Weight access
Ling 3.0 Flash
Open Weight
MAI-Thinking-1
Proprietary
License
Ling 3.0 Flash
Open Weight
MAI-Thinking-1
Proprietary
Release date
Ling 3.0 Flash
2026-07-23
MAI-Thinking-1
2026-06-02
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
- MAI-Thinking-1 has the higher public score estimate, 52.27 versus 52.2, but the 90% score intervals overlap.
- 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.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence30 rows
Agentic
MCP Atlas
Ling 3.0 Flash65.5%SourceMAI-Thinking-1—Not directly comparable
skillsBench
Ling 3.0 Flash44.8%SourceMAI-Thinking-1—Not directly comparable
BFCL v4
Ling 3.0 Flash73.0%SourceMAI-Thinking-1—Not directly comparable
WideResearch
Ling 3.0 Flash73.6%SourceMAI-Thinking-1—Not directly comparable
BrowseComp
Ling 3.0 Flash72.2%SourceMAI-Thinking-1—Not directly comparable
DRACO
Ling 3.0 Flash70.4%SourceMAI-Thinking-1—Not directly comparable
Terminal-Bench 2.1 (Vals)
Ling 3.0 Flash50.2%SourceMAI-Thinking-1—Not directly comparable
Terminal-Bench 2.0
Ling 3.0 Flash—MAI-Thinking-146%SourceNot directly comparable
Coding
SWE-bench Pro
Ling 3.0 Flash56.6%SourceMAI-Thinking-152.8%SourceLing 3.0 Flash leads this result
SWE Multilingual
Ling 3.0 Flash72.4%SourceMAI-Thinking-1—Not directly comparable
LiveCodeBench v5
Ling 3.0 Flash82.8%SourceMAI-Thinking-1—Not directly comparable
SciCode
Ling 3.0 Flash41.2%SourceMAI-Thinking-1—Not directly comparable
LiveCodeBench (Vals)
Ling 3.0 Flash84.0%SourceMAI-Thinking-1—Not directly comparable
SWE-bench (Vals)
Ling 3.0 Flash65.2%SourceMAI-Thinking-1—Not directly comparable
LiveCodeBench v6
Ling 3.0 Flash—MAI-Thinking-187.7%SourceNot directly comparable
SWE-bench Verified
Ling 3.0 Flash—MAI-Thinking-173.5%SourceNot directly comparable
Terminal-Bench 2.0
Ling 3.0 Flash—MAI-Thinking-146.0%SourceNot directly comparable
Reasoning
Graphwalks BFS 128K
Ling 3.0 Flash—MAI-Thinking-190%SourceNot directly comparable
Knowledge
GPQA
Ling 3.0 Flash85.0%SourceMAI-Thinking-184.2%SourceLing 3.0 Flash leads this result
GPQA-D
Ling 3.0 Flash85.0%SourceMAI-Thinking-184.2%SourceLing 3.0 Flash leads this result
HLE
Ling 3.0 Flash22.7%SourceMAI-Thinking-1—Not directly comparable
GPQA Diamond (Vals)
Ling 3.0 Flash84.8%SourceMAI-Thinking-1—Not directly comparable
MMLU-Pro (Vals)
Ling 3.0 Flash82.0%SourceMAI-Thinking-1—Not directly comparable
MMLU-Pro
Ling 3.0 Flash—MAI-Thinking-185%SourceNot directly comparable
SimpleQA
Ling 3.0 Flash—MAI-Thinking-131%SourceNot directly comparable
Math
AIME26
Ling 3.0 Flash93.2%SourceMAI-Thinking-194.5%SourceMAI-Thinking-1 leads this result
HMMT Feb 2026
Ling 3.0 Flash87.0%SourceMAI-Thinking-184.9%SourceLing 3.0 Flash leads this result
IMOAnswerBench
Ling 3.0 Flash83.7%SourceMAI-Thinking-1—Not directly comparable
AIME 2025
Ling 3.0 Flash—MAI-Thinking-197%SourceNot directly comparable
Instruction following
Frequently asked questions
Which is better, Ling 3.0 Flash or MAI-Thinking-1?
MAI-Thinking-1 has the higher public score estimate, 52.27 versus 52.2, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
Which is better for coding, Ling 3.0 Flash or MAI-Thinking-1?
MAI-Thinking-1 scores higher for coding on the public lane, 51.8 to 42.8. Ling 3.0 Flash and MAI-Thinking-1 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, Ling 3.0 Flash or MAI-Thinking-1?
MAI-Thinking-1 scores higher for agentic tasks on the public lane, 51.7 to 40. MAI-Thinking-1 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, Ling 3.0 Flash or MAI-Thinking-1?
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, Ling 3.0 Flash or MAI-Thinking-1?
Ling 3.0 Flash has the larger documented context window: 262K, compared with 256K.
Related comparisons
Last updated September 4, 2026
Watch Ling 3.0 Flash vs MAI-Thinking-1
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.