Knowledge
Directional only- Claude 3 Haiku
- 25.3
- Estimated · #183/184
- Ternary Bonsai 2 27B
- 50.6
- Estimated · #78/184
- Basis
- BenchAlign lane · 0 vs 3 public rows
- Reading
- Directional only
Claude 3 Haiku vs Ternary Bonsai 2 27B
Decision reading
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 resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Updated September 18, 2026. Rank says Ternary Bonsai 2 27B is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
Both of these models will change. Get the price, version and retirement notices for the pair, each with its source. Follow model changes
Share or export
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
Ternary Bonsai 2 27B
Ternary Bonsai 2 27B 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
Claude 3 Haiku is not ranked on the public lane for coding, so no winner is named for coding.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
Claude 3 Haiku is not ranked on the public lane for agentic, so no winner is named for agentic.
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. Claude 3 Haiku does not fit this workload in one request. Claude 3 Haiku has no published cached-input rate, so cached tokens use its listed input rate. Ternary Bonsai 2 27B has no comparable published API token rate.
Confidence: rate-fallback
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.
21 Ternary Bonsai 2 27B only
- Shared results
- 0
- Claude 3 Haiku only
- 0
- Ternary Bonsai 2 27B only
- 21
- Like-for-like categories
- 0 / 8
2 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Category results, on a stated basis
Each row shows the public-lane category score for both models: the BenchAlign lane for agentic, coding, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.
Instruction following
Directional only- Claude 3 Haiku
- 39.9
- #102/124
- Ternary Bonsai 2 27B
- 71.0
- #64/124
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Directional only
Agentic
Not comparable- Claude 3 Haiku
- Not ranked
- Ternary Bonsai 2 27B
- 49.9
- Estimated · #59/154
- Basis
- BenchAlign lane · 0 vs 3 public rows
- Reading
- Not comparable
Coding
Not comparable- Claude 3 Haiku
- Not ranked
- Ternary Bonsai 2 27B
- 49.9
- Estimated · #64/154
- Basis
- BenchAlign lane · 0 vs 4 public rows
- Reading
- Not comparable
Reasoning
Not comparable- Claude 3 Haiku
- 40.1
- Unranked · 2 rankable rows
- Ternary Bonsai 2 27B
- 73.9
- Unranked · 1 rankable row
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- Claude 3 Haiku
- Not ranked
- Ternary Bonsai 2 27B
- 76.8
- Unranked · 4 rankable rows
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Claude 3 Haiku
- Not ranked
- Ternary Bonsai 2 27B
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- Claude 3 Haiku
- 25.4
- Unranked · 1 rankable row
- Ternary Bonsai 2 27B
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | Claude 3 Haiku | Ternary Bonsai 2 27B | Basis | Reading |
|---|---|---|---|---|
| Knowledge | 25.3Estimated · #183/184 | 50.6Estimated · #78/184 | Directional onlyBenchAlign lane · 0 vs 3 public rows | Directional only |
| Instruction following | 39.9#102/124 | 71.0#64/124 | Directional onlyProvisional lane · 0 vs 1 weighted rows | Directional only |
| Agentic | Not ranked | 49.9Estimated · #59/154 | Not comparableBenchAlign lane · 0 vs 3 public rows | Not comparable |
| Coding | Not ranked | 49.9Estimated · #64/154 | Not comparableBenchAlign lane · 0 vs 4 public rows | Not comparable |
| Reasoning | 40.1Unranked · 2 rankable rows | 73.9Unranked · 1 rankable row | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | Not ranked | 76.8Unranked · 4 rankable rows | Not comparableProvisional lane · 0 vs 1 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multimodal | 25.4Unranked · 1 rankable row | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign) differ from the provisional-lane categories. Unranked scores sit on the lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
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
- Claude 3 Haiku
- $0.00088
- Fits in one request
- Ternary Bonsai 2 27B
- Self-hosted; infrastructure cost varies
- Fits in one request
Ternary Bonsai 2 27B has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- Claude 3 Haiku
- $0.01625
- Fits in one request
- Ternary Bonsai 2 27B
- Self-hosted; infrastructure cost varies
- Fits in one request
Ternary Bonsai 2 27B has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Claude 3 Haiku
- $0.0675
- Does not fit in one request
- Cached input priced at the published list-input rate
- Ternary Bonsai 2 27B
- Self-hosted; infrastructure cost varies
- Fits in one request
- Cached-input rate unavailable
Claude 3 Haiku does not fit this workload in one request. Claude 3 Haiku has no published cached-input rate, so cached tokens use its listed input rate. Ternary Bonsai 2 27B 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.
SpecificationClaude 3 HaikuTernary Bonsai 2 27B
Context window
Maximum documented context; output-token limits may be lower.
Claude 3 Haiku
200K
Ternary Bonsai 2 27B
API model ID
Claude 3 Haiku
Not sourced
Ternary Bonsai 2 27B
prism-ml/Ternary-Bonsai-2-27B-gguf
PrismML Bonsai 2 collectionCached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Claude 3 Haiku
Not published
Ternary Bonsai 2 27B
No comparable hosted API rate
PrismML Bonsai 2 collectionDocumented inputs
Claude 3 Haiku
Not sourced
Ternary Bonsai 2 27B
Not sourced
Documented outputs
Claude 3 Haiku
Not sourced
Ternary Bonsai 2 27B
Not sourced
Provider availability
Claude 3 Haiku
Not sourced
Ternary Bonsai 2 27B
Not sourced
Reasoning profile
Claude 3 Haiku
Non-Reasoning
Ternary Bonsai 2 27B
Reasoning
Weight access
Claude 3 Haiku
Proprietary
Ternary Bonsai 2 27B
Open Weight
License
Claude 3 Haiku
Proprietary
Ternary Bonsai 2 27B
Open Weight
Release date
Claude 3 Haiku
2024-03-01
Ternary Bonsai 2 27B
2026-09-17
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
- Ternary Bonsai 2 27B has the larger documented window (262K).
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 evidence21 rows
Agentic
Coding
LiveCodeBench v6
Claude 3 Haiku—Ternary Bonsai 2 27B90.1%SourceNot directly comparable
BigCodeBench
Claude 3 Haiku—Ternary Bonsai 2 27B58.1%SourceNot directly comparable
SWE-bench Verified
Claude 3 Haiku—Ternary Bonsai 2 27B60.8%SourceNot directly comparable
Terminal-Bench 2.1
Claude 3 Haiku—Ternary Bonsai 2 27B52.8%SourceNot directly comparable
Knowledge
Math
GSM8K
Claude 3 Haiku—Ternary Bonsai 2 27B96.7%SourceNot directly comparable
MATH-500
Claude 3 Haiku—Ternary Bonsai 2 27B98.8%SourceNot directly comparable
AIME 2025
Claude 3 Haiku—Ternary Bonsai 2 27B95%SourceNot directly comparable
AIME26
Claude 3 Haiku—Ternary Bonsai 2 27B95.8%SourceNot directly comparable
Multimodal
CharXiv (overall)
Claude 3 Haiku—Ternary Bonsai 2 27B80.0%SourceNot directly comparable
A-OKVQA
Claude 3 Haiku—Ternary Bonsai 2 27B86.8%SourceNot directly comparable
OmniDocBench 1.6
Claude 3 Haiku—Ternary Bonsai 2 27B89.1%SourceNot directly comparable
RealWorldQA
Claude 3 Haiku—Ternary Bonsai 2 27B80.1%SourceNot directly comparable
OCRBench V2
Claude 3 Haiku—Ternary Bonsai 2 27B56.9%SourceNot directly comparable
Instruction following
Questions
Which is better, Claude 3 Haiku or Ternary Bonsai 2 27B?
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, Claude 3 Haiku or Ternary Bonsai 2 27B?
Claude 3 Haiku is not ranked on the public lane for coding, so no winner is named for coding.
Which is better for agentic tasks, Claude 3 Haiku or Ternary Bonsai 2 27B?
Claude 3 Haiku is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.
Which costs less, Claude 3 Haiku or Ternary Bonsai 2 27B?
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, Claude 3 Haiku or Ternary Bonsai 2 27B?
Ternary Bonsai 2 27B has the larger documented context window: 262K, compared with 200K.
Related comparisons
Last updated September 18, 2026
Watch Claude 3 Haiku vs Ternary Bonsai 2 27B
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.