- Score
- 6.2 (+0.10 points)
- Total Cost (Current Price)
- $0.090 · 69.4% cheaper
- Response Time (avg)
- 3.60s · 32.0% faster
Thinkingmachines
Release: 2026-07-18
Tested on: 2026-10-01 03:32
thinkingmachines/inkling::none
975B total (41B active)MoEOpen source
Summary
Inkling scores 6.1 on AI BENCHY and ranks #264. It has 10.0 reliability, a 31.9% pass rate, $0.292 total cost, and 5.30s average response time.
What makes Inkling unique: It stands out most in Agentic, where it ranks #1, while Tool Calling is its weakest area at #14. It is notably fast compared with similar models.
Recommended alternatives
We recommend choosing one of these models instead:
- Score
- 6.6 (+0.49 points)
- Total Cost (Current Price)
- $0.121 · 58.9% cheaper
- Response Time (avg)
- 4.40s · 17.0% faster
- Score
- 5.9 (-0.15 points)
- Total Cost (Current Price)
- $0.080 · 72.9% cheaper
- Response Time (avg)
- 3.95s · 25.6% faster
Model facts
Researched on 2026-08-12
- Parameters
- 975B total (41B active)
- Architecture
- MoE
- Availability
- Open source
- License
- Apache-2.0
6.1
Consistency
9.6
10.0
Total Output Tokens
16,536
Total Input Tokens
236,599
Input Price
$0.950 / 1M
Output Price
$4.050 / 1M
Cache Read Price
$0.160 / 1M
Cache Write Price
N/A
Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.
Flaky tests
1
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#264 Thinking Machines: Inkling
none
Provider returned error
- Cost
- $0.000
- Time
- 5.3s
- Tokens
- 0 tok
Run history
| Tested on | Score | Reliability | Tests Correct | Total Cost | Compare |
|---|---|---|---|---|---|
| 2026-10-01 03:32 Re-test | 6.1 | 10.0 | $0.292 ↓ | Current run | |
| 2026-07-18 15:45 Initial run | 5.2 | 9.9 | $0.147 | Compare |
This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.
Run comparison
| Run | Benchmark coverage | Score | Consistency | Reliability | Tests Correct | Flaky tests | Total Output Tokens | Total Input Tokens | Total Cost | Response Time (avg) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-10-01 03:32 · Current run | 69/69 attempts | 6.1 | 9.6 | 10.0 | 7/23 | 1 | 16,536 | 236,599 | $0.292 | 5.30s |
| 2026-07-18 15:45 · Initial run | 66/66 attempts | 5.2 | 9.6 | 9.9 | 6/22 | 1 | 10,551 | 104,111 | $0.147 | 3.50s |
| Difference | — | +0.9 | 0.0 | +0.1 | +1 | 0 | +5985 | +132488 | +$0.145 | +1797ms |
Benchmark coverage differs: 69/69 attempts (Target: 3 repeats per test) versus 66/66 attempts (Target: 3 repeats per test). Totals and repeat-sensitive metrics are not directly comparable.
These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.
Price History
Historical pricing data for this model from OpenRouter.
| Date | Input Price | Output Price | Cache Read Price | Cache Write Price |
|---|---|---|---|---|
| 2026-07-18 15:56 | $1.000 / 1M | $4.050 / 1M | N/A | N/A |
| 2026-08-14 12:51 | $0.950 / 1M | $4.050 / 1M | N/A | N/A |
| 2026-10-02 09:43 | $0.950 / 1M | $4.050 / 1M | $0.160 / 1M | N/A |
Charts
Choose the first model, then click a second model to open a side-by-side page.
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Quick Compare
InklingnoneFree AvailablevsApodex 1.1 MinilowFree AvailableInklingnoneFree AvailablevsQwen3.5 Plus 2026-04-20noneInklingnoneFree AvailablevsTrinity Large ThinkingmediumInklingnoneFree AvailablevsStep 5 PreviewmediumInklingnoneFree AvailablevsGemini 3.5 FlashnoneInklingnoneFree AvailablevsGranite 4.2 8BmediumInklingnoneFree AvailablevsClaude Fable 5.1lowInklingnoneFree AvailablevsKAT-Coder-Pro V2.5defaultInklingnoneFree AvailablevsGemini 3.1 Flash Lite PreviewnoneInklingnoneFree AvailablevsApodex 1.1 MinimediumFree Available
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Agentic | 10.0 | 10.0 | |
| Anti-AI Tricks | 4.8 | 10.0 | |
| Coding | 4.5 | 10.0 | |
| Combined | 2.9 | 5.8 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 5.3 | 10.0 | |
| General Intelligence | 5.0 | 10.0 | |
| Instructions following | 6.3 | 10.0 | |
| Puzzle Solving | 5.6 | 9.9 | |
| Tool Calling | 3.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |