Coding
Like-for-like- Ornith-1.5-9B
- 61.7
- Qwen3.6 Plus
- 70.3
- Weighted basis
- 2 vs 2 rows
- Reading
- Qwen3.6 Plus leads
Ornith-1.5-9B vs Qwen3.6 Plus
Updated August 19, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
Qwen3.6 Plus has the higher public score, 64.81 versus 36.95, and the 90% score intervals do not overlap.
8 results are shared. Category rows based on different benchmark sets are marked directional and do not name a winner.
Which one for your work
Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.
Coding work
Code generation, repair, and software-engineering tasks
Qwen3.6 Plus
Qwen3.6 Plus leads on the same 2 weighted benchmark rows.
Confidence: limited
Long documents
Prompts that approach the documented context limit
Qwen3.6 Plus
Qwen3.6 Plus has the larger documented context window.
Confidence: documented
Show secondary and unsupported calls
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
No shared weighted benchmark basis supports a winner.
Confidence: limited
Chat turn cost
1K fresh input + 500 output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
Repository review cost
50K fresh input + 3K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
8 Ornith-1.5-9B only
8 Shared
36 Qwen3.6 Plus only
- Shared results
- 8
- Ornith-1.5-9B only
- 8
- Qwen3.6 Plus only
- 36
- Like-for-like categories
- 1 / 8
1 category uses different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Category results, on a stated basis
Each row states whether both averages use the same weighted benchmark set. Directional and not-comparable rows remain visible, but they never receive a winner in this template.
Knowledge
Directional only- Ornith-1.5-9B
- 29.1
- Qwen3.6 Plus
- 57.1
- Weighted basis
- 2 vs 4 rows
- Reading
- Directional only
Agentic
Not comparable- Ornith-1.5-9B
- 56.4
- Qwen3.6 Plus
- 61.6
- Weighted basis
- 1 vs 1 rows
- Reading
- Not comparable
Reasoning
Not comparable- Ornith-1.5-9B
- Not measured
- Qwen3.6 Plus
- 62.0
- Weighted basis
- 0 vs 1 rows
- Reading
- Not comparable
Math
Not comparable- Ornith-1.5-9B
- Not measured
- Qwen3.6 Plus
- 60.5
- Weighted basis
- 0 vs 4 rows
- Reading
- Not comparable
Multilingual
Not comparable- Ornith-1.5-9B
- Not measured
- Qwen3.6 Plus
- 84.7
- Weighted basis
- 0 vs 1 rows
- Reading
- Not comparable
Multimodal
Not comparable- Ornith-1.5-9B
- Not measured
- Qwen3.6 Plus
- 79.8
- Weighted basis
- 0 vs 2 rows
- Reading
- Not comparable
Instruction following
Not comparable- Ornith-1.5-9B
- Not measured
- Qwen3.6 Plus
- 82.3
- Weighted basis
- 0 vs 2 rows
- Reading
- Not comparable
| Category | Ornith-1.5-9B | Qwen3.6 Plus | Weighted basis | Reading |
|---|---|---|---|---|
| Coding | 61.7 | 70.3 | Like-for-like2 vs 2 rows | Qwen3.6 Plus leads |
| Knowledge | 29.1 | 57.1 | Directional only2 vs 4 rows | Directional only |
| Agentic | 56.4 | 61.6 | Not comparable1 vs 1 rows | Not comparable |
| Reasoning | Not measured | 62.0 | Not comparable0 vs 1 rows | Not comparable |
| Math | Not measured | 60.5 | Not comparable0 vs 4 rows | Not comparable |
| Multilingual | Not measured | 84.7 | Not comparable0 vs 1 rows | Not comparable |
| Multimodal | Not measured | 79.8 | Not comparable0 vs 2 rows | Not comparable |
| Instruction following | Not measured | 82.3 | Not comparable0 vs 2 rows | Not comparable |
Shape of the matched evidence
Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.
Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.
SWE-bench Pro
Coding
HLE
Knowledge
SWE-bench Verified
Coding
GPQA
Knowledge
What each workload costs
Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.
Chat turn
1K fresh input + 500 output tokens
- Ornith-1.5-9B
- Self-hosted; infrastructure cost varies
- Fits in one request
- Qwen3.6 Plus
- API rate not published
- Fits in one request
Ornith-1.5-9B has no comparable published API token rate. Qwen3.6 Plus has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- Ornith-1.5-9B
- Self-hosted; infrastructure cost varies
- Fits in one request
- Qwen3.6 Plus
- API rate not published
- Fits in one request
Ornith-1.5-9B has no comparable published API token rate. Qwen3.6 Plus has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Ornith-1.5-9B
- Self-hosted; infrastructure cost varies
- Fits in one request
- Cached-input rate unavailable
- Qwen3.6 Plus
- API rate not published
- Fits in one request
- Cached-input rate unavailable
Ornith-1.5-9B has no comparable published API token rate. Qwen3.6 Plus has no comparable published API token rate.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationOrnith-1.5-9BQwen3.6 Plus
Context window
Maximum documented context; output-token limits may be lower.
Ornith-1.5-9B
Qwen3.6 Plus
1M
API model ID
Ornith-1.5-9B
Not sourced
Qwen3.6 Plus
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Ornith-1.5-9B
No comparable hosted API rate
Ornith-1.5-9B model cardQwen3.6 Plus
No comparable hosted API rate
Documented inputs
Ornith-1.5-9B
Not sourced
Qwen3.6 Plus
Not sourced
Documented outputs
Ornith-1.5-9B
Not sourced
Qwen3.6 Plus
Not sourced
Provider availability
Ornith-1.5-9B
Not sourced
Qwen3.6 Plus
Not sourced
Reasoning profile
Ornith-1.5-9B
Reasoning
Qwen3.6 Plus
Reasoning
Weight access
Ornith-1.5-9B
Open Weight
Qwen3.6 Plus
Proprietary
License
Ornith-1.5-9B
Open Weight
Qwen3.6 Plus
Proprietary
Release date
Ornith-1.5-9B
2026-08-18
Qwen3.6 Plus
2026-04-02
If you already use one of these models
- Deployment change
- The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
- Quality signal
- Qwen3.6 Plus has the higher public score, 64.81 versus 36.95, and the 90% score intervals do not overlap.
- Workload cost
- A complete comparable API-rate estimate is not available for both models.
- Context tradeoff
- Qwen3.6 Plus has the larger documented window (1M).
Run the same representative tasks against both endpoints before changing production traffic.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence52 rows
Agentic
Terminal-Bench 2.1
Ornith-1.5-9B46.2%SourceQwen3.6 Plus—Not directly comparable
HLE w/ tools
Ornith-1.5-9B30.5%SourceQwen3.6 Plus—Not directly comparable
MCP Atlas
Ornith-1.5-9B54.2%SourceQwen3.6 Plus48.2%SourceOrnith-1.5-9B leads this result
Toolathlon-Verified
Ornith-1.5-9B41.2%SourceQwen3.6 Plus—Not directly comparable
WideResearch
Ornith-1.5-9B59.5%SourceQwen3.6 Plus74.3%SourceQwen3.6 Plus leads this result
BrowseComp
Ornith-1.5-9B56.4%SourceQwen3.6 Plus—Not directly comparable
Claw-Eval
Ornith-1.5-9B66.5%SourceQwen3.6 Plus58.8%SourceOrnith-1.5-9B leads this result
Terminal-Bench 2.0
Ornith-1.5-9B—Qwen3.6 Plus61.6%SourceNot directly comparable
QwenClawBench
Ornith-1.5-9B—Qwen3.6 Plus57.2%SourceNot directly comparable
τ³-bench results
Ornith-1.5-9B—Qwen3.6 Plus70.7%SourceNot directly comparable
VITA-Bench
Ornith-1.5-9B—Qwen3.6 Plus44.3%SourceNot directly comparable
DeepPlanning
Ornith-1.5-9B—Qwen3.6 Plus41.5%SourceNot directly comparable
Toolathlon
Ornith-1.5-9B—Qwen3.6 Plus39.8%SourceNot directly comparable
MCP-Tasks
Ornith-1.5-9B—Qwen3.6 Plus74.1%SourceNot directly comparable
Gert Labs
Ornith-1.5-9B—Qwen3.6 Plus50.60%SourceNot directly comparable
ResearchClawBench
Ornith-1.5-9B—Qwen3.6 Plus18.0%SourceNot directly comparable
Coding
Terminal-Bench 2.1
Ornith-1.5-9B46.2%SourceQwen3.6 Plus—Not directly comparable
SWE-bench Verified
Ornith-1.5-9B70.6%SourceQwen3.6 Plus78.8%SourceQwen3.6 Plus leads this result
SWE-bench Pro
Ornith-1.5-9B47.5%SourceQwen3.6 Plus56.6%SourceQwen3.6 Plus leads this result
SWE Multilingual
Ornith-1.5-9B54.4%SourceQwen3.6 Plus73.8%SourceQwen3.6 Plus leads this result
NL2Repo
Ornith-1.5-9B32.4%SourceQwen3.6 Plus—Not directly comparable
LiveCodeBench v6
Ornith-1.5-9B—Qwen3.6 Plus87.1%SourceNot directly comparable
Vibe Code Bench
Ornith-1.5-9B—Qwen3.6 Plus25.56%SourceNot directly comparable
EEBench
Ornith-1.5-9B—Qwen3.6 Plus12.7%SourceNot directly comparable
Reasoning
Knowledge
GPQA
Ornith-1.5-9B86.4%SourceQwen3.6 Plus90.4%SourceQwen3.6 Plus leads this result
GPQA-D
Ornith-1.5-9B86.4%SourceQwen3.6 Plus—Not directly comparable
HLE
Ornith-1.5-9B20.2%SourceQwen3.6 Plus28.8%SourceQwen3.6 Plus leads this result
HLE w/o tools
Ornith-1.5-9B20.2%SourceQwen3.6 Plus—Not directly comparable
SuperGPQA
Ornith-1.5-9B—Qwen3.6 Plus71.6%SourceNot directly comparable
MMLU-Pro
Ornith-1.5-9B—Qwen3.6 Plus88.5%SourceNot directly comparable
MMLU-Redux
Ornith-1.5-9B—Qwen3.6 Plus94.5%SourceNot directly comparable
C-Eval
Ornith-1.5-9B—Qwen3.6 Plus93.3%SourceNot directly comparable
Math
AIME26
Ornith-1.5-9B—Qwen3.6 Plus95.3%SourceNot directly comparable
HMMT Feb 2025
Ornith-1.5-9B—Qwen3.6 Plus96.7%SourceNot directly comparable
HMMT Nov 2025
Ornith-1.5-9B—Qwen3.6 Plus94.6%SourceNot directly comparable
HMMT Feb 2026
Ornith-1.5-9B—Qwen3.6 Plus87.8%SourceNot directly comparable
MMAnswerBench
Ornith-1.5-9B—Qwen3.6 Plus83.8%SourceNot directly comparable
FrontierMath v2 (Tiers 1-3)
Ornith-1.5-9B—Qwen3.6 Plus26.207%SourceNot directly comparable
FrontierMath v2 (Tier 4)
Ornith-1.5-9B—Qwen3.6 Plus8.333%SourceNot directly comparable
Multilingual
Multimodal
MMMU
Ornith-1.5-9B—Qwen3.6 Plus86.0%SourceNot directly comparable
MMMU-Pro
Ornith-1.5-9B—Qwen3.6 Plus78.8%SourceNot directly comparable
MathVision
Ornith-1.5-9B—Qwen3.6 Plus88.0%SourceNot directly comparable
VideoMMMU
Ornith-1.5-9B—Qwen3.6 Plus84.0%SourceNot directly comparable
ScreenSpot Pro
Ornith-1.5-9B—Qwen3.6 Plus68.2%SourceNot directly comparable
CharXiv
Ornith-1.5-9B—Qwen3.6 Plus81.5%SourceNot directly comparable
V*
Ornith-1.5-9B—Qwen3.6 Plus96.9%SourceNot directly comparable
Instruction following
Frequently asked questions
Which is better, Ornith-1.5-9B or Qwen3.6 Plus?
Qwen3.6 Plus has the higher public score, 64.81 versus 36.95, and the 90% score intervals do not overlap. That is the clearest overall quality signal in the current public data.
Which is better for coding, Ornith-1.5-9B or Qwen3.6 Plus?
Qwen3.6 Plus leads the like-for-like coding comparison across 2 shared weighted benchmark rows.
Which is better for agentic tasks, Ornith-1.5-9B or Qwen3.6 Plus?
The published evidence does not provide a shared weighted agentic tasks basis for both models, so BenchLM does not name a agentic tasks winner.
Which costs less, Ornith-1.5-9B or Qwen3.6 Plus?
Both models do not have comparable published API token rates, so this page does not name a universal price winner.
Which has the larger context window, Ornith-1.5-9B or Qwen3.6 Plus?
Qwen3.6 Plus has the larger documented context window: 1M, compared with 262K.
Related comparisons
Last updated August 19, 2026
Watch Ornith-1.5-9B vs Qwen3.6 Plus
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.