Note: Overall leaderboard rankings may not reflect true model quality — individual benchmarks give a clearer picture. ARC-Challenge MMLU GPQA GSM8K Artificial Analysis Intelligence Index v4.1
← Back to leaderboard

Thinking Machines Lab: inkling

7 benchmarks
Country of originUSA

Leaderboard position

#152
Overall rank (of 1121 models)
2052
Elo rating
7
Benchmarks
Top 13.6%
Percentile
In Thinking Machines Lab (of 3 models)

Benchmark highlights

Nearest competitor from another company

The model from another company with the most similar benchmark scores.

appeared as nearest in 2 of 7 benchmarks

Benchmarks

Predicted scores

Estimated from 25 similar models and the global Elo rating. These are projections, not measured results.

Benchmark Predicted Confidence Based on
IFBench ~73.55 61% Xiaomi: MiMo-V2.5 Pro, NVIDIA Corporation: nvidia-nemotron-3-ultra, Qwen: Qwen3.7 Max
Terminal-Bench v2.1 ~63.76 61% Xiaomi: MiMo-V2.5 Pro, MiniMax: MiniMax M3, Meta: muse-glimmer-30b
SWE-bench Pro ~53.72 61% Xiaomi: MiMo-V2.5 Pro, Qwen: qwen3.6-27b, reflection: beam-1.0
Artificial Analysis Intelligence Index v4.0 (Maximum Reasoning) ~43.14 61% Xiaomi: MiMo-V2.5 Pro, NVIDIA Corporation: nvidia-nemotron-3-ultra, Qwen: qwen3.6-27b
AIME 2025 ~100 60% Mistral AI: mistral-medium-3.5-128b
HMMT Feb 2026 ~88.25 60% Qwen: qwen3.6-27b, Z.ai: GLM 5.2
GPQA Diamond ~84.73 60% Xiaomi: MiMo-V2.5 Pro, Qwen: qwen3.6-27b, Meta: muse-glimmer-30b
Humanity's Last Exam (no tools) ~32.88 60% Xiaomi: MiMo-V2.5 Pro, Qwen: qwen3.6-27b, Qwen: qwen3.8-27b
HumanEval ~95.9 60% OpenAI: GPT-3.5 Turbo
MMLU ~92.5 60% OpenAI: GPT-3.5 Turbo
Humanity's Last Exam (with tools) ~44.62 60% Meta: muse-spark-1.1, Google: Gemma 4 31B Instruct, Anthropic: claude-sonnet-5
GSM8K ~99.6 60% Xiaomi: MiMo-V2.5 Pro
LiveCodeBench v6 ~83.29 60% Xiaomi: MiMo-V2.5 Pro, Qwen: qwen3.6-27b, Qwen: qwen3.8-27b
MMMU-Pro ~75.7 60% Qwen: qwen3.6-27b, MiniMax: MiniMax M3, Meta: muse-glimmer-30b
MATH ~97.9 60% Xiaomi: MiMo-V2.5 Pro, OpenAI: GPT-3.5 Turbo
BBH ~88.4 60% Xiaomi: MiMo-V2.5 Pro
ARC-Challenge ~97.3 60% Xiaomi: MiMo-V2.5 Pro
HellaSwag ~95.4 60% Xiaomi: MiMo-V2.5 Pro
CowQA ~97.22 60% Google: Gemma 4 31B Instruct
GPQA ~83.65 60% Xiaomi: MiMo-V2.5 Pro, Z.ai: GLM 5.2, OpenAI: GPT-3.5 Turbo
SuperGPQA ~69.64 60% Qwen: qwen3.6-27b, OpenAI: gpt-oss-120b
ParseBench ~65.89 60% Qwen: qwen3.8-27b, Google: Gemma 4 31B Instruct, Anthropic: claude-opus-5.5
Text Arena (Snapshot from 20 june 2026) ~1447.76 60% Xiaomi: MiMo-V2.5 Pro, Qwen: Qwen3.7 Max, MiniMax: MiniMax M3
LLMArena (llmarena.ru) (Snapshot from 19 june 2026) ~1124.59 60% OpenAI: gpt-oss-120b
WinoGrande ~92 60% Xiaomi: MiMo-V2.5 Pro