Key Specifications
Parameters
124.0B
Context
131.1K
Release Date
August 4, 2026
Average Score
68.5%
Timeline
Key dates in the model's history
Announcement
August 4, 2026
Last Update
September 10, 2026
Today
September 20, 2026
Technical Specifications
Parameters
124.0B
Training Tokens
-
Knowledge Cutoff
-
Family
-
Capabilities
MultimodalZeroEval
Pricing & Availability
Input (per 1M tokens)
$0.06
Output (per 1M tokens)
$0.18
Max Input Tokens
131.1K
Max Output Tokens
131.1K
Supported Features
Function CallingStructured OutputCode ExecutionWeb SearchBatch InferenceFine-tuning
Benchmark Results
Model performance metrics across various tests and benchmarks
Other Tests
Specialized benchmarks
AA-LCR
Official model-card evaluation table; detailed setup not specified. • Self-reported
AIME 2026
Official model-card evaluation table; detailed setup not specified. • Self-reported
Artifacts Bench
Official model-card evaluation table; detailed setup not specified. • Self-reported
BFCL-V4
Official model-card evaluation table; detailed setup not specified. • Self-reported
BrowseComp
Internal single-agent search harness; context resume at 64K via trajectory summarization and history discard; average pass@1. • Self-reported
DRACO
Internal search-agent harness; official per-question rubrics averaged across questions; Claude Opus 4.6 scoring model. • Self-reported
GDPval-AA
GDPval v2-AA Elo on the public 220-task set using the official Stirrup harness; 250-turn limit; 5-hour timeout. • Self-reported
HMMT Feb 26
Official model-card evaluation table; detailed setup not specified. • Self-reported
IFBench
Official model-card evaluation table; detailed setup not specified. • Self-reported
IMO-AnswerBench
Official model-card evaluation table; detailed setup not specified. • Self-reported
LiveCodeBench v6
Official model-card evaluation table; detailed setup not specified. • Self-reported
MCP Atlas
500-task public set; official v1 harness; 20-turn limit; Gemini-2.5-Pro claim-coverage judge. • Self-reported
Multi-IF
Official model-card evaluation table; detailed setup not specified. • Self-reported
SkillsBench
Kilo Code harness on 87 default runnable tasks, excluding external-API-dependent tasks; average of 3 runs. • Self-reported
SWE-bench Multilingual
OpenHands agent harness with tailored prompts; temperature=0.6, top_p=0.95, max_new_tokens=32K; 256K context. • Self-reported
SWE-Bench Pro
OpenHands agent harness with tailored prompts; temperature=0.6, top_p=0.95, max_new_tokens=32K; 256K context. • Self-reported
Tau3 Banking
Artificial Analysis-aligned protocol; GPT-5.4-mini with medium reasoning used for user simulation and natural-language assertion judging. • Self-reported
Terminal-Bench 2.1
Artificial Analysis protocol; default Terminus 2 harness; 2-hour timeout; preserve-thinking JSON parser; 3-run task mean; temperature=0.6, top_p=1.0, max_new_tokens=32K; 256K context. • Self-reported
WideSearch
Internal basic-ReAct single-agent search harness; official prompt and GPT-4.1 judge on the corrected dataset; average pass@1. • Self-reported
License & Metadata
License
unknown
Announcement Date
August 4, 2026
Last Updated
September 10, 2026
Compare Ling 3.0 Flash
All comparisonsSimilar Models
All Models
Ling 3.0 Flash Fin
InclusionAI
124.0B
Released:Sep 2026
Price:$0.06/1M tokens
K-EXAONE-236B-A23B
LG AI Research
236.0B
Released:Dec 2025
Price:$0.60/1M tokens
Atria Dawn Preview
Shanghai AI Laboratory
744.0B
Released:Sep 2026
Laguna S 2.1
Poolside
118.0B
Released:Jul 2026
Price:$0.10/1M tokens
GLM-5.3
Zhipu AI
753.0B
Released:Aug 2026
Price:$1.40/1M tokens
Kimi K2 Base
Moonshot AI
1.0T
Best score:0.9 (MMLU)
Released:Jan 2025
GLM-5.2
Zhipu AI
753.0B
Best score:0.9 (GPQA)
Released:Jun 2026
Price:$1.40/1M tokens
MiniMax M2
MiniMax
230.0B
Best score:0.8 (GPQA)
Released:Oct 2025
Price:$0.30/1M tokens
Recommendations are based on similarity of characteristics: developer organization, multimodality, parameter size, and benchmark performance. Choose a model to compare or go to the full catalog to browse all available AI models.