Skip to content

Models / Inkling Small

Thinkingmachines

Inkling Small

22 published results from 3 sources. Each card shows where the number comes from and what it does not measure. The overall leaderboard combines them; here each stands alone.

Provider: Thinkingmachines
Sources: 3
Our benchmarks: 1
Price per million tokens: $0.45 in · $1.20 out
OpenRouter list price, 1 Oct 2026 · 524,288-token context

Measured by Spring Prompt

Measured by Spring Prompt · BulletBench

$0.0075

Cost per game · rank 7 of 23

Unit: US dollars, lower is better
Configuration: Inkling Small (no reasoning), none reasoning
Measured: 1 Oct 2026
Not shown: Not your cost: prices are those charged on the run date.

Measured by Spring Prompt · BulletBench

0.0%

Games lost on time · rank 1 of 23

Unit: % of games, lower is better
Configuration: Inkling Small (no reasoning), none reasoning
Measured: 1 Oct 2026
Not shown: Not a business skill: chess against an engine on a real clock, used here as a speed-under-pressure signal.

Measured by Spring Prompt · BulletBench

7.2%

Invalid moves · rank 23 of 23

Unit: % of moves, lower is better
Configuration: Inkling Small (no reasoning), none reasoning
Measured: 1 Oct 2026
Not shown: Not a business skill: chess against an engine on a real clock, used here as a speed-under-pressure signal.

Measured by Spring Prompt · BulletBench

529

Ladder Elo · rank 3 of 23

Unit: ladder Elo, higher is better
Range: 393 to 652
Sample: 12 games
Configuration: Inkling Small (no reasoning), none reasoning
Measured: 1 Oct 2026
Not shown: Not a business skill: chess against an engine on a real clock, used here as a speed-under-pressure signal.

Measured by Spring Prompt · BulletBench

0.6 s

Median move time · rank 4 of 23

Unit: milliseconds, lower is better
Configuration: Inkling Small (no reasoning), none reasoning
Measured: 1 Oct 2026
Not shown: Not general response speed: replies are one short move.

Measured by Spring Prompt · BulletBench

$0.0077

Cost per game · rank 8 of 14

Unit: US dollars, lower is better
Configuration: Inkling Small (no reasoning), none reasoning
Measured: 1 Oct 2026
Not shown: Not your cost: prices are those charged on the run date.

Measured by Spring Prompt · BulletBench

0.0%

Games lost on time · rank 1 of 14

Unit: % of games, lower is better
Configuration: Inkling Small (no reasoning), none reasoning
Measured: 1 Oct 2026
Not shown: Not a business skill: chess against an engine on a real clock, used here as a speed-under-pressure signal.

Measured by Spring Prompt · BulletBench

5.3%

Invalid moves · rank 14 of 14

Unit: % of moves, lower is better
Configuration: Inkling Small (no reasoning), none reasoning
Measured: 1 Oct 2026
Not shown: Not a business skill: chess against an engine on a real clock, used here as a speed-under-pressure signal.

Measured by Spring Prompt · BulletBench

571

Ladder Elo · rank 1 of 14

Unit: ladder Elo, higher is better
Range: 428 to 698
Sample: 12 games
Configuration: Inkling Small (no reasoning), none reasoning
Measured: 1 Oct 2026
Not shown: Not a business skill: chess against an engine on a real clock, used here as a speed-under-pressure signal.

Measured by Spring Prompt · BulletBench

0.6 s

Median move time · rank 5 of 14

Unit: milliseconds, lower is better
Configuration: Inkling Small (no reasoning), none reasoning
Measured: 1 Oct 2026
Not shown: Not general response speed: replies are one short move.

Reported by others

Reported by Arena (formerly LMArena)

-0.21

Confirmed task success · rank 43 of 46

Unit: IPS effect estimate, higher is better
Range: -0.25 to -0.17
Sample: 7096 observations
Configuration: Inkling Small
Measured: 28 Sep 2026
Not shown: Not a success rate: the estimated effect of choosing this model as the agent's orchestrator, against an even mix of the models tested, inside Arena's own harness.

Reported by Arena (formerly LMArena)

-0.21

Praise over complaint · rank 43 of 46

Unit: IPS effect estimate, higher is better
Range: -0.24 to -0.17
Sample: 2752 observations
Configuration: Inkling Small
Measured: 28 Sep 2026
Not shown: Not a success rate: the estimated effect of choosing this model as the agent's orchestrator, against an even mix of the models tested, inside Arena's own harness.

Reported by Arena (formerly LMArena)

-0.12

Steerability · rank 41 of 46

Unit: IPS effect estimate, higher is better
Range: -0.15 to -0.08
Sample: 9247 observations
Configuration: Inkling Small
Measured: 28 Sep 2026
Not shown: Not a success rate: the estimated effect of choosing this model as the agent's orchestrator, against an even mix of the models tested, inside Arena's own harness.

Reported by Arena (formerly LMArena)

-0.00

Tool grounding · rank 30 of 46

Unit: IPS effect estimate, higher is better
Range: -0.01 to -0.00
Sample: 419271 observations
Configuration: Inkling Small
Measured: 28 Sep 2026
Not shown: Not a success rate: the estimated effect of choosing this model as the agent's orchestrator, against an even mix of the models tested, inside Arena's own harness.

Reported by Arena (formerly LMArena)

1,425

Overall · rank 105 of 177

Unit: Arena rating, higher is better
Range: 1,421 to 1,429
Sample: 24435 votes
Configuration: Inkling Small
Measured: 25 Sep 2026
Not shown: Not an error rate: claims that cannot be checked on the web are skipped, and preference still carries most of the weight.

Reported by Arena (formerly LMArena)

1,408

Business, management and finance · rank 110 of 402

Unit: Arena rating, higher is better
Range: 1,398 to 1,417
Sample: 4737 votes
Configuration: Inkling Small
Measured: 25 Sep 2026
Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Reported by Arena (formerly LMArena)

1,313

Creative writing · rank 187 of 407

Unit: Arena rating, higher is better
Range: 1,304 to 1,323
Sample: 5116 votes
Configuration: Inkling Small
Measured: 25 Sep 2026
Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Reported by Arena (formerly LMArena)

1,445

Expert prompts · rank 89 of 359

Unit: Arena rating, higher is better
Range: 1,433 to 1,456
Sample: 2955 votes
Configuration: Inkling Small
Measured: 25 Sep 2026
Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Reported by Arena (formerly LMArena)

1,393

Instruction following · rank 126 of 409

Unit: Arena rating, higher is better
Range: 1,386 to 1,400
Sample: 9156 votes
Configuration: Inkling Small
Measured: 25 Sep 2026
Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Reported by Arena (formerly LMArena)

1,405

Overall · rank 133 of 409

Unit: Arena rating, higher is better
Range: 1,400 to 1,410
Sample: 24758 votes
Configuration: Inkling Small
Measured: 25 Sep 2026
Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Reported by Arena (formerly LMArena)

1,344

Writing, literature and language · rank 174 of 408

Unit: Arena rating, higher is better
Range: 1,335 to 1,352
Sample: 6751 votes
Configuration: Inkling Small
Measured: 25 Sep 2026
Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Reported by SimpleQA Verified (Epoch AI)

19.1%

Correct answers · rank 73 of 85

Unit: % of questions, higher is better
Configuration: Inkling Small (xhigh)
Measured: 27 Aug 2026
Not shown: Not answers grounded in your documents; tests what the model remembers.

Compare Inkling Small with