Skip to main content

Model comparison

Inkling vs Ornith-1.0-397B

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
3.0pts
winning →
DeepReinforce AI
72/100
0 category wins2 category wins

Verified leaderboard positions: Inkling #17; Ornith-1.0-397B unranked

Evidence parity. Inkling and Ornith-1.0-397B share 4 comparable benchmark results. 2 of 8 categories are comparable. 12 results are unique to Inkling; 3 to Ornith-1.0-397B.

Updated July 15, 2026
Shared results
4
Inkling only
12
Ornith-1.0-397B only
3
Comparable categories
2 / 8

Pick Ornith-1.0-397B if you want the stronger benchmark profile. Inkling only becomes the better choice if you need the larger 1M context window or you would rather avoid the extra latency and token burn of a reasoning model.

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

Ornith-1.0-397B has the cleaner provisional overall profile here, landing at 72 versus 69. It is a real lead, but still close enough that category-level strengths matter more than the headline number.

Ornith-1.0-397B's sharpest advantage is in agentic, where it averages 77.5 against 69.4. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 63.8% to 77.5%.

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-1.0-397B. That is roughly Infinityx on output cost alone. Ornith-1.0-397B 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-1.0-397B.

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-1.0-397B
CategoryInklingΔOrnith-1.0-397B
AgenticInkling69.4Margin 8.1Ornith-1.0-397B77.5
CodingInkling68.6Margin 6.0Ornith-1.0-397B74.6
KnowledgeInkling51.7MarginNo overlapOrnith-1.0-397BNot measured
MathInkling97.1MarginNo overlapOrnith-1.0-397BNot measured
MultimodalInkling76.5MarginNo overlapOrnith-1.0-397BNot measured
Inst. FollowingInkling79.8MarginNo overlapOrnith-1.0-397BNot measured

Decisive benchmark drivers

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

More
A · InklingB · Ornith-1.0-397B
  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 63.8%B 77.5%
    Winner: Ornith-1.0-397BΔ 13.7
    Terminal-Bench 2.0: Inkling scored 63.8%; Ornith-1.0-397B scored 77.5%. Ornith-1.0-397B wins this benchmark.
  2. SWE-bench Pro

    Coding
    Source ↗
    A 54.3%B 62.2%
    Winner: Ornith-1.0-397BΔ 7.9
    SWE-bench Pro: Inkling scored 54.3%; Ornith-1.0-397B scored 62.2%. Ornith-1.0-397B wins this benchmark.
  3. SWE-bench Verified

    Coding
    Source ↗
    A 77.6%B 82.4%
    Winner: Ornith-1.0-397BΔ 4.8
    SWE-bench Verified: Inkling scored 77.6%; Ornith-1.0-397B scored 82.4%. Ornith-1.0-397B wins this benchmark.

Operational comparison

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

MetricInklingOrnith-1.0-397BComparison
Input / output priceUSD per 1M tokensInkling$1.87 input / $4.68 outputOrnith-1.0-397B$0 input / $0 outputOrnith-1.0-397B has the lower combined listed price.
Generation speedtokens per secondInklingNot availableOrnith-1.0-397BNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenInklingNot availableOrnith-1.0-397BNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensInkling1MOrnith-1.0-397B256KInkling lists the larger context window.

Benchmark Deep Dive

AgenticOrnith-1.0-397B wins
BenchmarkInklingOrnith-1.0-397BResult
Terminal-Bench 2.0Source 63.8%77.5%Ornith-1.0-397B leads
BrowseCompSource 77.1%Not comparable
MCP AtlasSource 74.1%Not comparable
Design Arena Agentic Web DevSource 1258Not comparable
Claw-EvalSource 77.1%Not comparable
CodingOrnith-1.0-397B wins
BenchmarkInklingOrnith-1.0-397BResult
SWE-bench VerifiedSource 77.6%82.4%Ornith-1.0-397B leads
SWE-bench ProSource 54.3%62.2%Ornith-1.0-397B leads
Terminal-Bench 2.0Source 63.8%77.5%Ornith-1.0-397B leads
SWE MultilingualSource 78.9%Not comparable
NL2RepoSource 48.2%Not comparable
Knowledge
BenchmarkInklingOrnith-1.0-397BResult
GPQASource 87.9%Not comparable
GPQA-DSource 87.9%Not comparable
HLESource 46%Not comparable
HLE w/o toolsSource 30%Not comparable
Math
BenchmarkInklingOrnith-1.0-397BResult
AIME26Source 97.1%Not comparable
Multimodal
BenchmarkInklingOrnith-1.0-397BResult
MMMU-ProSource 73.5%Not comparable
CharXivSource 82%Not comparable
CharXiv w/o toolsSource 78.1%Not comparable
Inst. Following
BenchmarkInklingOrnith-1.0-397BResult
IFBenchSource 79.8%Not comparable
Frequently Asked Questions (3)

Which is better, Inkling or Ornith-1.0-397B?

Ornith-1.0-397B is ahead on BenchLM's provisional leaderboard, 72 to 69. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 63.8% and 77.5%.

Which is better for coding, Inkling or Ornith-1.0-397B?

Ornith-1.0-397B has the edge for coding in this comparison, averaging 74.6 versus 68.6. 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-1.0-397B?

Ornith-1.0-397B has the edge for agentic tasks in this comparison, averaging 77.5 versus 69.4. 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.