- Rank
- #110 of 140
- Percentile
- Benchmarks
- 8
Model evidence profile
Inkling-Small
Thinking Machines Lab · Open Weight · Hybrid
currentsupported
- Overall public score
- 64.02
- Source rank
- #45
- Evidence coverage
- 8 benchmarks · 2 sources
Strongest published evidencePublic overall score 64.02 at source rank #45.
Validate before choosingValidate the selected route price, context limits, and evidence freshness before choosing.
Revision benchmark_3b14dc55ef5307cfe91356d3ea348101 · Published Aug 30, 2026 · Checked Aug 30, 2026 · stale
Relative field position
Capability radar
Percentiles use eligible source ranks. Missing axes remain unavailable and never become zero.
- Agentic percentile
- 21.6 percentileRank #110 of 140
- Coding percentile
- 60.4 percentileRank #58 of 145
- Instruction Following percentile
- 90.2 percentileRank #5 of 42
- Knowledge percentile
- Knowledge: Unavailable
- Math percentile
- Math: Unavailable
- Multimodal grounded percentile
- 20.6 percentileRank #28 of 35
- Overall percentile
- Overall: Unavailable
- Reasoning percentile
- Reasoning: Unavailable
Published measurements
Category scores
Scores retain their source units; percentile and rank appear only for eligible fields.
- Rank
- #58 of 145
- Percentile
- Benchmarks
- 8
- Rank
- #5 of 42
- Percentile
- Benchmarks
- 8
- Rank
- Not ranked
- Percentile
- Benchmarks
- 8
- Rank
- Not ranked
- Percentile
- Benchmarks
- 8
- Rank
- #28 of 35
- Percentile
- Benchmarks
- 8
- Rank
- #45
- Percentile
- Benchmarks
- 8
- Rank
- Not ranked
- Percentile
- Benchmarks
- 8
Route-specific facts
Pricing and specifications
Conflicting routes remain separate and attributable.
thinking-machines-labbenchlm:inkling-small
primary- Input / 1M
- $0.58
- Cached input / 1M
- $0.12
- Output / 1M
- $1.44
- Context
- 1,000,000
- Context window
- 1,000,000
- Maximum output
- Unavailable
- Input modalities
- Unavailable
- Output modalities
- Unavailable
- Release date
- 2026-07-30
- Self hosting
- Not verified
Auditable evidence
Benchmark ledger
Display values, source ranks, and provenance remain visible without implying unsupported aggregate weight.
agentic
| Score | Rank | Weight | Last Updated | Source |
|---|---|---|---|---|
| 40.37 | #110 | Not published | Aug 29, 2026 | BenchLM |
coding
| Score | Rank | Weight | Last Updated | Source |
|---|---|---|---|---|
| 53.58 | #58 | Not published | Aug 29, 2026 | BenchLM |
instructionFollowing
| Score | Rank | Weight | Last Updated | Source |
|---|---|---|---|---|
| 92.80 | #5 | Not published | Aug 29, 2026 | BenchLM |
knowledge
| Score | Rank | Weight | Last Updated | Source |
|---|---|---|---|---|
| 69.90 | Not ranked | Not published | Aug 29, 2026 | BenchLM |
math
| Score | Rank | Weight | Last Updated | Source |
|---|---|---|---|---|
| 77.00 | Not ranked | Not published | Aug 29, 2026 | BenchLM |
multimodalGrounded
| Score | Rank | Weight | Last Updated | Source |
|---|---|---|---|---|
| 41.60 | #28 | Not published | Aug 29, 2026 | BenchLM |
reasoning
| Score | Rank | Weight | Last Updated | Source |
|---|---|---|---|---|
| 41.70 | Not ranked | Not published | Aug 29, 2026 | BenchLM |
overall
| Score | Rank | Weight | Last Updated | Source |
|---|---|---|---|---|
| 64.02 | #45 | Not published | Aug 29, 2026 | BenchLM |
Related evidence