- Rank
- #114 of 140
- Percentile
- Benchmarks
- 7
Model evidence profile
Inkling
Thinking Machines Lab · Open Weight · Hybrid
currentsupported
- Overall public score
- 67.02
- Source rank
- #31
- Evidence coverage
- 7 benchmarks · 2 sources
Strongest published evidencePublic overall score 67.02 at source rank #31.
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
- 18.7 percentileRank #114 of 140
- Coding percentile
- 14.6 percentileRank #124 of 145
- Instruction Following percentile
- 65.9 percentileRank #15 of 42
- Knowledge percentile
- 46.3 percentileRank #30 of 55
- Math percentile
- Math: Unavailable
- Multimodal grounded percentile
- 17.6 percentileRank #29 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
- #124 of 145
- Percentile
- Benchmarks
- 7
- Rank
- #15 of 42
- Percentile
- Benchmarks
- 7
- Rank
- #30 of 55
- Percentile
- Benchmarks
- 7
- Rank
- Not ranked
- Percentile
- Benchmarks
- 7
- Rank
- #29 of 35
- Percentile
- Benchmarks
- 7
- Rank
- #31
- Percentile
- Benchmarks
- 7
Route-specific facts
Pricing and specifications
Conflicting routes remain separate and attributable.
thinking-machines-labbenchlm:inkling
primary- Input / 1M
- $1.87
- Cached input / 1M
- $0.37
- Output / 1M
- $4.68
- Context
- 1,000,000
- Context window
- 1,000,000
- Maximum output
- Unavailable
- Input modalities
- Unavailable
- Output modalities
- Unavailable
- Release date
- 2026-07-15
- 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 |
|---|---|---|---|---|
| 39.54 | #114 | Not published | Aug 29, 2026 | BenchLM |
coding
| Score | Rank | Weight | Last Updated | Source |
|---|---|---|---|---|
| 42.04 | #124 | Not published | Aug 29, 2026 | BenchLM |
instructionFollowing
| Score | Rank | Weight | Last Updated | Source |
|---|---|---|---|---|
| 88.60 | #15 | Not published | Aug 29, 2026 | BenchLM |
knowledge
| Score | Rank | Weight | Last Updated | Source |
|---|---|---|---|---|
| 66.80 | #30 | Not published | Aug 29, 2026 | BenchLM |
math
| Score | Rank | Weight | Last Updated | Source |
|---|---|---|---|---|
| 79.00 | Not ranked | Not published | Aug 29, 2026 | BenchLM |
multimodalGrounded
| Score | Rank | Weight | Last Updated | Source |
|---|---|---|---|---|
| 41.50 | #29 | Not published | Aug 29, 2026 | BenchLM |
overall
| Score | Rank | Weight | Last Updated | Source |
|---|---|---|---|---|
| 67.02 | #31 | Not published | Aug 29, 2026 | BenchLM |
Related evidence