LLaDA2.2-mini

LLaDA2.2-mini is a reasoning model from InclusionAI in the LLaDA2.2 family. 7 benchmarks count toward its score, in 5 categories.

partialShows if the model has enough results for an index.
IndexOverall score out of 100.Unranked
CoverageShare of the index weight with results.70%
SpeedOutput tokens per second.
Input / 1MUS dollars per 1M input tokens.Free
Output / 1MUS dollars per 1M output tokens.Free
ContextMaximum tokens in one request.128K
EloLMArena rating and rank.N/A

The index is a score out of 100. The ± range shows how much it can change.

CapabilitiesScore per category, out of 100.

Out of 100
AgenticMulti-step tasks with tools.
40.1
CodingCode writing and repair.
5.0
ReasoningLogic problems and puzzles.
N/A
MultimodalTasks with images and text.
N/A
KnowledgeFacts and expert knowledge.
19.2
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
5.0
MathMath problems.
9.4

Results

7 counted
BenchmarkThe test name.CategoryThe capability that the test measures.ResultThe score from the publisher.IndexThis result as a score out of 100.RunThe settings of the run.DateDate of the result.Published byThe source of the result.
PinchBenchAgentic62.3%Kilo Code
τ²-Bench Tool-Agent-User EvaluationAgentic57.5%40.1Victor Barres et al.
Claw-EvalAgentic57.2%48.3Bowen Ye et al.
Berkeley Function Calling Leaderboard v4Agentic47.7%32.0Arcee AI
GPQA DiamondKnowledge44.4%19.2David Rein et al.
AIME 2026Math35.0%9.4Qwen
LongBench v2Reasoning35.0%LongBench v2 authors
LiveCodeBench v6Coding28.1%5.0LiveCodeBench maintainers
Instruction Following BenchmarkInstruction24.9%5.0Benchmark authors

7 benchmarks count, from 7 of 9 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 authors

More from InclusionAI

Ling 3.0 Flash52.4Ling 3.0 Flash VL52.5Ling 3.0 Flash FP851.0Ling 2.6 Flash37.4Ling 3.0 Flash FinUnranked