Ling 3.0 Flash

Ling 3.0 Flash is a reasoning model from InclusionAI in the Ling 3.0 family. 28 benchmarks count toward its score, in 6 categories.

availableShows if the model has enough results for an index.
IndexOverall score. 50 is the middle.52.4 ±4.6
CoverageShare of the index weight with results.85%
SpeedOutput tokens per second.97/s
Input / 1MUS dollars per 1M input tokens.$0.021
Output / 1MUS dollars per 1M output tokens.$0.063
ContextMaximum tokens in one request.262K
EloLMArena rating and rank.N/A

50 is the middle of the board. The range shows the doubt in the index.

CapabilitiesScore per category. 50 is the middle.

50 is the middle
AgenticMulti-step tasks with tools.
56.5
CodingCode writing and repair.
51.3
ReasoningLogic problems and puzzles.
50.3
MultimodalTasks with images and text.
N/A
KnowledgeFacts and expert knowledge.
50.1
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
52.7
MathMath problems.
54.1

Results

28 counted
BenchmarkThe test name.CategoryThe capability that the test measures.ResultThe score from the publisher.IndexThis result on the index scale.RunThe settings of the run.DateDate of the result.Published byThe source of the result.
AIME 2026Math93.2%52.9Qwen
Harvard-MIT Mathematics Tournament February 2026Math87.0%55.2Qwen
Artificial Analysis GPQA DiamondKnowledge85.5%56.2Artificial Analysis
Graduate-Level Google-Proof Q&AKnowledge85.0%56.7David Rein et al.
GPQA DiamondKnowledge85.0%56.7David Rein et al.
GPQA DiamondKnowledge84.8%56.61 Sept 2026Vals AI
GPQA DiamondKnowledge84.8%56.61 Sept 2026Vals AI
LiveCodeBenchCoding84.0%60.71 Sept 2026Vals AI
LiveCodeBenchCoding84.0%60.71 Sept 2026Vals AI
IMOAnswerBenchMath83.7%DeepSeek-AI
LiveCodeBench v5Coding82.8%LiveCodeBench maintainers
MMLU ProKnowledge82.0%49.71 Sept 2026Vals AI
MMLU ProKnowledge82.0%49.71 Sept 2026Vals AI
Instruction Following BenchmarkInstruction74.5%52.7Benchmark authors
WideResearchAgentic73.6%58.9Qwen
Berkeley Function Calling Leaderboard v4Agentic73.0%58.0Arcee AI
Artificial Analysis Long Context ReasoningReasoning73.0%58.7Artificial Analysis
BrowseCompAgentic72.2%60.5OpenAI
Data Research and Analysis with Complex OperationsAgentic70.4%Anthropic
MCP AtlasAgentic65.5%57.5OpenAI
SWE-benchCoding65.2%49.81 Sept 2026Vals AI
SWE-benchCoding65.2%49.81 Sept 2026Vals AI
Terminal-Bench 2.1 (provider run)Agentic57.0%57.7DeepSeek-AI
Terminal-Bench 2.1 (provider run)Agentic57.0%57.7DeepSeek-AI
SWE-bench ProCoding56.6%58.7Xiang Deng et al.
Artificial Analysis Coding IndexCoding50.6%54.7Artificial Analysis
Terminal-Bench 2.1Agentic50.2%53.721 Sept 2026Vals AI
Terminal-Bench 2.1Agentic50.2%53.721 Sept 2026Vals AI
Artificial Analysis SciCodeCoding42.0%51.2Artificial Analysis
Scientific Code BenchmarkCoding41.2%51.2Benchmark authors
Artificial Analysis Tau3-BankingAgentic28.0%50.8Artificial Analysis
SkillsBenchCoding27.9%46.7OpenHands11 Sept 2026Vals AI
SkillsBenchCoding27.9%46.7OpenHands11 Sept 2026Vals AI
Artificial Analysis Intelligence IndexKnowledge24.9%53.6Artificial Analysis
Artificial Analysis Humanity's Last ExamKnowledge23.7%50.3Artificial Analysis
Humanity's Last ExamKnowledge22.7%48.0Center for AI Safety et al.
Artificial Analysis Agentic IndexAgentic21.0%54.3Artificial Analysis
Artificial Analysis Omniscience AccuracyKnowledge18.2%36.4Artificial Analysis
Vibe Code Bench v1.1Coding2.9%43.4OpenHands21 Sept 2026Vals AI
Vibe Code Bench v1.1Coding2.9%43.4OpenHands21 Sept 2026Vals AI
Critical Physics TasksReasoning1.7%41.9Artificial Analysis
Code MigrationCoding0.0%44.921 Sept 2026Vals AI
Code MigrationCoding0.0%44.921 Sept 2026Vals AI

28 benchmarks count, from 40 of 43 results. A grey row does not count. Too few models took that benchmark.

Sources

BenchLM benchmark aggregationUsed with attribution; per-benchmark results credited to their original authorsOpenRouter, collected directlyNo licence statedVals AI, collected directlyNo licence stated. Read from the public leaderboard and credited to Vals AI

Same level, lower price

Qwen3.8-Flash-Next66.4 · Freedots3-note Preview65.5 · FreeApodex 1.1 Mini59.1 · Free

More from InclusionAI

Ling 3.0 Flash VL52.5Ling 3.0 Flash FP851.0Ling 2.6 Flash37.4Ling 3.0 Flash FinUnrankedLing 3.0 TinyUnranked