Agentic
Not comparable- GPT Realtime 1.5
- Not measured
- Ornith-1.0-35B
- 64.2
- Weighted basis
- 0 vs 1 rows
- Reading
- Not comparable
Model comparison
GPT Realtime 1.5 vs Ornith-1.0-35B
Updated August 4, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. Use the documented cost, context, and runtime rows instead.
0 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.
Long documents
Prompts that approach the documented context limit
Ornith-1.0-35B
Ornith-1.0-35B has the larger documented context window.
Confidence: documented
Show secondary and unsupported calls
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
No shared weighted benchmark basis supports a winner.
Confidence: limited
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
The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. GPT Realtime 1.5 does not fit this workload in one request. Ornith-1.0-35B has no comparable published API token rate.
Confidence: listed-rates
Repository review cost
50K fresh input + 3K output tokens
Not enough matched evidence
The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. GPT Realtime 1.5 does not fit this workload in one request. Ornith-1.0-35B has no comparable published API token rate.
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.
7 Ornith-1.0-35B only
- Shared results
- 0
- GPT Realtime 1.5 only
- 0
- Ornith-1.0-35B only
- 7
- Like-for-like categories
- 0 / 8
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.
Coding
Not comparable- GPT Realtime 1.5
- Not measured
- Ornith-1.0-35B
- 65.9
- Weighted basis
- 0 vs 2 rows
- Reading
- Not comparable
Reasoning
Not comparable- GPT Realtime 1.5
- Not measured
- Ornith-1.0-35B
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Knowledge
Not comparable- GPT Realtime 1.5
- Not measured
- Ornith-1.0-35B
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Math
Not comparable- GPT Realtime 1.5
- Not measured
- Ornith-1.0-35B
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Multilingual
Not comparable- GPT Realtime 1.5
- Not measured
- Ornith-1.0-35B
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Multimodal
Not comparable- GPT Realtime 1.5
- Not measured
- Ornith-1.0-35B
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Instruction following
Not comparable- GPT Realtime 1.5
- Not measured
- Ornith-1.0-35B
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
| Category | GPT Realtime 1.5 | Ornith-1.0-35B | Weighted basis | Reading |
|---|---|---|---|---|
| Agentic | Not measured | 64.2 | Not comparable0 vs 1 rows | Not comparable |
| Coding | Not measured | 65.9 | Not comparable0 vs 2 rows | Not comparable |
| Reasoning | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Knowledge | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Math | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Multilingual | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Multimodal | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Instruction following | Not measured | Not measured | Not comparable0 vs 0 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.
A shared-evidence shape is not available.
BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.
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
- GPT Realtime 1.5
- $0.012
- Fits in one request
- Ornith-1.0-35B
- Self-hosted; infrastructure cost varies
- Fits in one request
Ornith-1.0-35B has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- GPT Realtime 1.5
- $0.248
- Does not fit in one request
- Ornith-1.0-35B
- Self-hosted; infrastructure cost varies
- Fits in one request
GPT Realtime 1.5 does not fit this workload in one request. Ornith-1.0-35B has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- GPT Realtime 1.5
- $0.32
- Does not fit in one request
- Ornith-1.0-35B
- Self-hosted; infrastructure cost varies
- Fits in one request
- Cached-input rate unavailable
GPT Realtime 1.5 does not fit this workload in one request. Ornith-1.0-35B 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.
SpecificationGPT Realtime 1.5Ornith-1.0-35B
Context window
Maximum documented context; output-token limits may be lower.
GPT Realtime 1.5
Ornith-1.0-35B
256K
API model ID
GPT Realtime 1.5
gpt-realtime-1.5
OpenAI model documentationOrnith-1.0-35B
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
GPT Realtime 1.5
$0.4 per 1M cached input tokens
OpenAI model documentationOrnith-1.0-35B
No comparable hosted API rate
Documented inputs
GPT Realtime 1.5
Not sourced
Ornith-1.0-35B
Not sourced
Documented outputs
GPT Realtime 1.5
Not sourced
Ornith-1.0-35B
Not sourced
Provider availability
GPT Realtime 1.5
Not sourced
Ornith-1.0-35B
Not sourced
Reasoning profile
GPT Realtime 1.5
Non-Reasoning
Ornith-1.0-35B
Reasoning
Weight access
GPT Realtime 1.5
Proprietary
Ornith-1.0-35B
Open Weight
License
GPT Realtime 1.5
Proprietary
Ornith-1.0-35B
Open Weight
Release date
GPT Realtime 1.5
2026-02-01
Ornith-1.0-35B
2026-06-01
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
- The public evidence has no benchmark result shared by both models, so it does not support a quality verdict.
- Workload cost
- A complete comparable API-rate estimate is not available for both models.
- Context tradeoff
- Ornith-1.0-35B has the larger documented window (256K).
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 evidence7 rows
Agentic
Coding
SWE-bench Verified
GPT Realtime 1.5—Ornith-1.0-35B75.6%SourceNot directly comparable
SWE-bench Pro
GPT Realtime 1.5—Ornith-1.0-35B50.4%SourceNot directly comparable
SWE Multilingual
GPT Realtime 1.5—Ornith-1.0-35B69.3%SourceNot directly comparable
NL2Repo
GPT Realtime 1.5—Ornith-1.0-35B34.6%SourceNot directly comparable
Terminal-Bench 2.0
GPT Realtime 1.5—Ornith-1.0-35B64.2%SourceNot directly comparable
Frequently asked questions
Which is better, GPT Realtime 1.5 or Ornith-1.0-35B?
The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. The page therefore keeps the decision tied to the specific documented workload.
Which is better for coding, GPT Realtime 1.5 or Ornith-1.0-35B?
The published evidence does not provide a shared weighted coding basis for both models, so BenchLM does not name a coding winner.
Which is better for agentic tasks, GPT Realtime 1.5 or Ornith-1.0-35B?
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, GPT Realtime 1.5 or Ornith-1.0-35B?
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, GPT Realtime 1.5 or Ornith-1.0-35B?
Ornith-1.0-35B has the larger documented context window: 256K, compared with 32K.
Related comparisons
Last updated August 4, 2026
Watch GPT Realtime 1.5 vs Ornith-1.0-35B
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.