Skip to main content

Model comparison

Inkling vs Ornith-1.0-9B

Data verified

Head-to-head evidence from 4 shared benchmark results across 2 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

Thinking Machines Lab
69/100
Margin
20.0pts
← winning
DeepReinforce AI
49/100
2 category wins0 category wins

Verified leaderboard positions: Inkling #17; Ornith-1.0-9B unranked

Evidence parity. Inkling and Ornith-1.0-9B share 4 comparable benchmark results. 2 of 8 categories are comparable. 12 results are unique to Inkling; 3 to Ornith-1.0-9B.

Updated July 15, 2026
Shared results
4
Inkling only
12
Ornith-1.0-9B only
3
Comparable categories
2 / 8

Pick Inkling if you want the stronger benchmark profile. Ornith-1.0-9B only becomes the better choice if you want the cheaper token bill or you want the stronger reasoning-first profile.

Confidence note. This is a partial-evidence comparison with 4 shared benchmark results across 2 evidence categories; 2 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Inkling is clearly ahead on the provisional aggregate, 69 to 49. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Inkling's sharpest advantage is in agentic, where it averages 69.4 against 43.1. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 63.8% to 43.1%.

Inkling is also the more expensive model on tokens at $1.87 input / $4.68 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Ornith-1.0-9B. That is roughly Infinityx on output cost alone. Ornith-1.0-9B is the reasoning model in the pair, while Inkling is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. Inkling gives you the larger context window at 1M, compared with 256K for Ornith-1.0-9B.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for Inkling and Ornith-1.0-9B
CategoryInklingΔOrnith-1.0-9B
AgenticInkling69.4Margin 26.3Ornith-1.0-9B43.1
CodingInkling68.6Margin 9.4Ornith-1.0-9B59.2
KnowledgeInkling51.7MarginNo overlapOrnith-1.0-9BNot measured
MathInkling97.1MarginNo overlapOrnith-1.0-9BNot measured
MultimodalInkling76.5MarginNo overlapOrnith-1.0-9BNot measured
Inst. FollowingInkling79.8MarginNo overlapOrnith-1.0-9BNot measured

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

More
A · InklingB · Ornith-1.0-9B
  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 63.8%B 43.1%
    Winner: InklingΔ 20.7
    Terminal-Bench 2.0: Inkling scored 63.8%; Ornith-1.0-9B scored 43.1%. Inkling wins this benchmark.
  2. SWE-bench Pro

    Coding
    Source ↗
    A 54.3%B 42.9%
    Winner: InklingΔ 11.4
    SWE-bench Pro: Inkling scored 54.3%; Ornith-1.0-9B scored 42.9%. Inkling wins this benchmark.
  3. SWE-bench Verified

    Coding
    Source ↗
    A 77.6%B 69.4%
    Winner: InklingΔ 8.2
    SWE-bench Verified: Inkling scored 77.6%; Ornith-1.0-9B scored 69.4%. Inkling wins this benchmark.

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricInklingOrnith-1.0-9BComparison
Input / output priceUSD per 1M tokensInkling$1.87 input / $4.68 outputOrnith-1.0-9B$0 input / $0 outputOrnith-1.0-9B has the lower combined listed price.
Generation speedtokens per secondInklingNot availableOrnith-1.0-9BNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenInklingNot availableOrnith-1.0-9BNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensInkling1MOrnith-1.0-9B256KInkling lists the larger context window.

Benchmark Deep Dive

AgenticInkling wins
BenchmarkInklingOrnith-1.0-9BResult
Terminal-Bench 2.0Source 63.8%43.1%Inkling leads
BrowseCompSource 77.1%Not comparable
MCP AtlasSource 74.1%Not comparable
Design Arena Agentic Web DevSource 1258Not comparable
Claw-EvalSource 63.1%Not comparable
CodingInkling wins
BenchmarkInklingOrnith-1.0-9BResult
SWE-bench VerifiedSource 77.6%69.4%Inkling leads
SWE-bench ProSource 54.3%42.9%Inkling leads
Terminal-Bench 2.0Source 63.8%43.1%Inkling leads
SWE MultilingualSource 52%Not comparable
NL2RepoSource 27.2%Not comparable
Knowledge
BenchmarkInklingOrnith-1.0-9BResult
GPQASource 87.9%Not comparable
GPQA-DSource 87.9%Not comparable
HLESource 46%Not comparable
HLE w/o toolsSource 30%Not comparable
Math
BenchmarkInklingOrnith-1.0-9BResult
AIME26Source 97.1%Not comparable
Multimodal
BenchmarkInklingOrnith-1.0-9BResult
MMMU-ProSource 73.5%Not comparable
CharXivSource 82%Not comparable
CharXiv w/o toolsSource 78.1%Not comparable
Inst. Following
BenchmarkInklingOrnith-1.0-9BResult
IFBenchSource 79.8%Not comparable
Frequently Asked Questions (3)

Which is better, Inkling or Ornith-1.0-9B?

Inkling is ahead on BenchLM's provisional leaderboard, 69 to 49. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 63.8% and 43.1%.

Which is better for coding, Inkling or Ornith-1.0-9B?

Inkling has the edge for coding in this comparison, averaging 68.6 versus 59.2. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Inkling or Ornith-1.0-9B?

Inkling has the edge for agentic tasks in this comparison, averaging 69.4 versus 43.1. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 15, 2026

The AI models change fast. We track them for you.

A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.