Inkling

thinkingmachines/inkling-20260715

Thinking Machines: Inkling is a multimodal model that processes text, image, and audio inputs to generate text outputs. It has a context length of 524,288 tokens, supports tool use and reasoning, and is available as an open-weight model. The pricing is $1 per million input tokens and $4.05 per million output tokens.

  • tool use
  • reasoning
  • open-weight

At a glance

providerthinkingmachines
releasedJul 15, 2026
context524K
input / M$1

Specifications

What the API gives you

Context window
524K tokens
Max output
472K tokens
Input price
$1 / 1M tokens
Output price
$4.05 / 1M tokens
Cache read
$0.17 / 1M tokens
Modalities
text, image, audio → text
Knowledge cutoff
—
Released
Jul 15, 2026

Measured evidence

Public benchmark record

Design Arena Coding
1193 Elo2026-11-15
Design Arena UI
1188 Elo2026-11-15
Design Arena Web-app Agent
1172 Elo2026-11-15
Design Arena Website
1215 Elo2026-11-15
FrontierMath Tiers 1-3 (Epoch AI)‡
33.3% ± 2.82026-08-06xhigh effort, evaluated 2026-08-06
GPQA Diamond (Epoch AI)‡
88.3% ± 1.92026-08-05xhigh effort, evaluated 2026-08-05
LiveBench Coding
71.0%2026-10-18
LiveBench Language
73.5%2026-10-18
LiveBench Math
88.4%2026-10-18
LiveBench Reasoning
78.3%2026-10-18
LMArena Agent
-17.32026-11-11
LMArena Creative Writing
1395 Elo2026-11-11
LMArena Long Query
1437 Elo2026-11-11
LMArena Math
1481 Elo2026-11-11
LMArena Text
1442 Elo2026-11-11
LMArena Text Factuality
1452 Elo2026-11-11
LMArena WebDev
1414 Elo2026-11-11
OTIS Mock AIME (Epoch AI)‡
88.9% ± 3.92026-08-05xhigh effort, evaluated 2026-08-05
SimpleQA Verified (Epoch AI)‡
40.3% ± 1.62026-08-27xhigh effort, evaluated 2026-08-27
tau2-bench (1.0.1)‡
25%2026-07-24max effort, evaluated 2026-07-24
Terminal-Bench (4.1)‡
0%2026-11-15mini-swe-agent, none effort, evaluated 2026-11-13

LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open. Design Arena uses blind human preference. ‡ Submitted scaffold plus model result. Compare the harness and effort settings, not only the model name.

Open-weight model on Hugging Face.

Task evidence

How broad is the support?

Each status is exact to this model version and the selected task. Official release claims remain provisional.

  • Best LLM for Competition MathEstablished evidence

    100% of intended weighted task evidence across 4 independent sources. 6 of 6 configured evaluation feeds currently have results.

  • Best LLM for Business WritingEstablished evidence

    100% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • 100% of intended weighted task evidence across 3 independent sources. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Marketing CopyEstablished evidence

    100% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Chat & RoleplayEstablished evidence

    100% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Creative WritingEstablished evidence

    100% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

Show all 41 tasks
  • Best LLM for WritingEstablished evidence

    100% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • 100% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Math & ReasoningEstablished evidence

    100% of intended weighted task evidence across 5 independent sources. 7 of 7 configured evaluation feeds currently have results.

  • 100% of intended weighted task evidence across 3 independent sources. 6 of 6 configured evaluation feeds currently have results.

  • Best LLM for Frontend & UIEstablished evidence

    91% of intended weighted task evidence across 3 independent sources. 6 of 6 configured evaluation feeds currently have results.

  • Best LLM for Code CompletionEstablished evidence

    79% of intended weighted task evidence across 2 independent sources. 3 of 3 configured evaluation feeds currently have results.

  • Best LLM for Agentic CodingEstablished evidence

    69% of intended weighted task evidence across 4 independent sources. 7 of 7 configured evaluation feeds currently have results.

  • Best LLM for Autonomous AgentsEstablished evidence

    67% of intended weighted task evidence across 3 independent sources. 6 of 6 configured evaluation feeds currently have results.

  • Best LLM for CodingEstablished evidence

    64% of intended weighted task evidence across 4 independent sources. 7 of 7 configured evaluation feeds currently have results.

  • 64% of intended weighted task evidence across 2 independent sources. 2 of 3 configured evaluation feeds currently have results.

  • Best LLM for AI AgentsEstablished evidence

    59% of intended weighted task evidence across 4 independent sources. 9 of 9 configured evaluation feeds currently have results.

  • 58% of intended weighted task evidence across 2 independent sources. 6 of 7 configured evaluation feeds currently have results.

  • Best LLM for Fast SummariesEstablished evidence

    58% of intended weighted task evidence across 2 independent sources. 2 of 3 configured evaluation feeds currently have results.

  • Best Value LLMEstablished evidence

    58% of intended weighted task evidence across 2 independent sources. 2 of 3 configured evaluation feeds currently have results.

  • 50% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.

  • 50% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for TranslationEstablished evidence

    50% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for Hermes AgentEstablished evidence

    48% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for OpenHandsEstablished evidence

    48% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for GooseEstablished evidence

    48% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for OpenClawEstablished evidence

    48% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best Local LLM for CodingEstablished evidence

    47% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • 40% of intended weighted task evidence across 2 independent sources. 5 of 6 configured evaluation feeds currently have results.

  • Best LLM for SummarizationEstablished evidence

    40% of intended weighted task evidence across 2 independent sources. 5 of 6 configured evaluation feeds currently have results.

  • Best Cheap LLM for High VolumeEstablished evidence

    40% of intended weighted task evidence across 2 independent sources. 2 of 3 configured evaluation feeds currently have results.

  • Cheapest Capable LLMEstablished evidence

    40% of intended weighted task evidence across 2 independent sources. 2 of 3 configured evaluation feeds currently have results.

  • 35% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.

  • 35% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.

  • 33% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Grounded RAGEstablished evidence

    29% of intended weighted task evidence across 2 independent sources. 5 of 7 configured evaluation feeds currently have results.

  • 22% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LMArena Document. 5 of 6 configured evaluation feeds currently have results.

  • 21% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Route reliability or Structured-output eval. 1 of 3 configured evaluation feeds currently have results.

  • Best LLM for Massive ContextProvisional evidence

    20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or LongBench v2. 2 of 3 configured evaluation feeds currently have results.

  • 17% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or OSWorld Verified. 3 of 3 configured evaluation feeds currently have results.

  • 11% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Vision or VLMEvalKit tasks. 2 of 3 configured evaluation feeds currently have results.

Recommendation coverage

Where this model appears

Not currently included in a published recommendation. The task evidence panel above says exactly what is confirmed and what is still missing.

Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.