Claude Haiku 4.5 vs gpt-oss-20b
Claude Haiku 4.5 leads gpt-oss-20b on the Artificial Analysis Intelligence Index, 16.9 to 10.0, and gpt-oss-20b costs 33.3x less per output token ($0.15 vs $5.00 per million). Updated October 22, 2026; 47 benchmarks have a result for both.
Claude Haiku 4.5 or gpt-oss-20b: which to pick
Only Claude Haiku 4.5 has a coding score, 35.6 on the Vibe Coding Index; gpt-oss-20b has none, so the two cannot be ranked on coding.
Pick gpt-oss-20b for output tokens 33.3x cheaper ($0.15 vs $5.00 per million) and work measured by LiveCodeBench (Vals AI) or AIME, where it leads.
- Shared results
- 47
- Claude Haiku 4.5 only
- 51
- gpt-oss-20b only
- 16
- Like-for-like categories
- 7 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Only Claude Haiku 4.5 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
Claude Haiku 4.5
Claude Haiku 4.5 leads, 16.9 against 10.0.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Claude Haiku 4.5 has a AA Agentic Index result, 8.0.
Directional only
Reasoning
GPQA Diamond
Claude Haiku 4.5
Claude Haiku 4.5 leads, 72.2% against 68.9%.
Same board, both measured
Math
AIME
gpt-oss-20b
gpt-oss-20b leads, 86.0% against 82.7%.
Same board, both measured
Knowledge
MMLU Pro
Claude Haiku 4.5
Claude Haiku 4.5 leads, 78.7% against 71.6%.
Same board, both measured
Web design
Design Arena: websites
Claude Haiku 4.5
Claude Haiku 4.5 leads, 1122 against 852.
Same board, both measured
Long documents
Listed context window
Claude Haiku 4.5
Claude Haiku 4.5 takes 200K tokens against 131K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
gpt-oss-20b
Claude Haiku 4.5 $0.0035, gpt-oss-20b $0.0001 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Claude Haiku 4.5 has the number, $0.56.
Directional only
At a glance
- Coding index
- Claude Haiku 4.5 35.6 from 4 benchmarks, gpt-oss-20b not benchmarked.
- Widest category
- Web design, 28.8 points apart on average over 2 shared benchmarks.
- Widest single gap
- LiveCodeBench (Vals AI): Claude Haiku 4.5 41.2% against gpt-oss-20b 80.4%, 39.2 points apart on a 0 to 100 scale.
- Output price
- Claude Haiku 4.5 $5.00 against gpt-oss-20b $0.15 per million output tokens, 33.3x apart.
- Context window
- Claude Haiku 4.5 takes 200K tokens, gpt-oss-20b 131K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Claude Haiku 4.5 | Bars | gpt-oss-20b | Ties |
|---|---|---|---|---|
| Coding | 4 | 1 | ||
| Intelligence | 2 | 0 | ||
| Reasoning | 5 | 0 | ||
| Math | 4 | 1 | ||
| Knowledge | 9 | 1 | ||
| Web design | 2 | 0 | ||
| General | 18 | 0 | ||
| All shared boards | 44 | 3 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index41
| Benchmark | Claude Haiku 4.5 | gpt-oss-20b | Leader |
|---|---|---|---|
| SWE-bench Verified | 66.6% | Not measured | Only Claude Haiku 4.5 measured |
| SWE-bench Multilingual | 64.7% | Not measured | Only Claude Haiku 4.5 measured |
| LiveBench coding | 48.1% | Not measured | Only Claude Haiku 4.5 measured |
| LMArena WebDev | 1330 | Not measured | Only Claude Haiku 4.5 measured |
| AA Coding Index | 43.9 | Not measured | Only Claude Haiku 4.5 measured |
| LiveCodeBench (Vals AI) | 41.2% | 80.4% | gpt-oss-20b |
| SWE-bench Verified (Vals AI) | 66.6% | Not measured | Only Claude Haiku 4.5 measured |
| Vibe Code Bench (Vals AI) | 11.4% | Not measured | Only Claude Haiku 4.5 measured |
| Code migration (Vals AI) | 7.5% | Not measured | Only Claude Haiku 4.5 measured |
| ProgramBench (Vals AI) | 0.0% | Not measured | Only Claude Haiku 4.5 measured |
| Terminal-Bench 2.1 (Vals AI) | 43.8% | Not measured | Only Claude Haiku 4.5 measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 77.7% | Only gpt-oss-20b measured |
| SciCode | Not measured | 38.9% | Only gpt-oss-20b measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 10.6% | Only gpt-oss-20b measured |
| Terminal-Bench | 35.5% | 3.4% | Claude Haiku 4.5 |
| WeirdML | 45.4% | 40.9% | Claude Haiku 4.5 |
| ALE-Bench | Not measured | 566.0 | Only gpt-oss-20b measured |
| LMArena Text: coding | 1454 | 1307 | Claude Haiku 4.5 |
| LMArena Text: software and IT | 1439 | 1311 | Claude Haiku 4.5 |
| LMArena WebDev: React | 1326 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena WebDev: HTML | 1318 | Not measured | Only Claude Haiku 4.5 measured |
| Neither model has a result on the other 22 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Haiku 4.5 | gpt-oss-20b | Leader |
|---|---|---|---|
| AA Intelligence Index | 16.9 | 10.0 | Claude Haiku 4.5 |
| Epoch Capabilities Index | 142.2 | 137.7 | Claude Haiku 4.5 |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index15 boards, none shared
| Benchmark | Claude Haiku 4.5 | gpt-oss-20b | Leader |
|---|---|---|---|
| AA Agentic Index | 8.0 | Not measured | Only Claude Haiku 4.5 measured |
| LiveBench research | 42.2% | Not measured | Only Claude Haiku 4.5 measured |
| LiveBench browser | 40.0% | Not measured | Only Claude Haiku 4.5 measured |
| LiveBench long agentic | 11.1% | Not measured | Only Claude Haiku 4.5 measured |
| Finance Agent (Vals AI) | 31.0% | Not measured | Only Claude Haiku 4.5 measured |
| Tax Agent Bench (Vals AI) | 5.9% | Not measured | Only Claude Haiku 4.5 measured |
| Legal Research Bench (Vals AI) | 10.6% | Not measured | Only Claude Haiku 4.5 measured |
| Excel Modeling Benchmark (Vals AI) | 22.7% | Not measured | Only Claude Haiku 4.5 measured |
| τ²-Bench Telecom | Not measured | 60.2% | Only gpt-oss-20b measured |
| BALROG | 31.2% | Not measured | Only Claude Haiku 4.5 measured |
| DeepResearch Bench | 45.5% | Not measured | Only Claude Haiku 4.5 measured |
| Vending-Bench 2 | $459 | Not measured | Only Claude Haiku 4.5 measured |
| Berkeley Function Calling Leaderboard (BFCL) | 68.7% | Not measured | Only Claude Haiku 4.5 measured |
| BrowseComp-Plus | Not measured | 50.6% | Only gpt-oss-20b measured |
| MCP Atlas | 40.2% | Not measured | Only Claude Haiku 4.5 measured |
| Neither model has a result on the other 27 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Claude Haiku 4.5 | gpt-oss-20b | Leader |
|---|---|---|---|
| GPQA Diamond | 72.2% | 68.9% | Claude Haiku 4.5 |
| LiveBench reasoning | 61.7% | Not measured | Only Claude Haiku 4.5 measured |
| MMMU Pro (Vals AI) | 46.1% | Not measured | Only Claude Haiku 4.5 measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 68.8% | Only gpt-oss-20b measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 11.0% | Only gpt-oss-20b measured |
| GPQA Diamond (Epoch AI run) | 71.2% | 60.8% | Claude Haiku 4.5 |
| ARC-AGI | 47.7% | Not measured | Only Claude Haiku 4.5 measured |
| ARC-AGI-2 | 4.0% | Not measured | Only Claude Haiku 4.5 measured |
| Chess puzzles | 8.0% | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: hard prompts | 1421 | 1274 | Claude Haiku 4.5 |
| LMArena Text: expert | 1443 | 1258 | Claude Haiku 4.5 |
| LMArena Text: hard prompts in English | 1435 | 1292 | Claude Haiku 4.5 |
| Kagi LLM Benchmark | Not measured | 53.2% | Only gpt-oss-20b measured |
| Neither model has a result on the other 10 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index41
| Benchmark | Claude Haiku 4.5 | gpt-oss-20b | Leader |
|---|---|---|---|
| AIME | 82.7% | 86.0% | gpt-oss-20b |
| MATH 500 (Vals AI) | Not measured | 94.2% | Only gpt-oss-20b measured |
| MGSM (Vals AI) | 92.2% | 89.0% | Claude Haiku 4.5 |
| AA Math Index | Not measured | 89.3 | Only gpt-oss-20b measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 89.3% | Only gpt-oss-20b measured |
| OTIS Mock AIME | 66.7% | 65.3% | Claude Haiku 4.5 |
| MATH level 5 | 96.4% | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: math | 1398 | 1317 | Claude Haiku 4.5 |
| LMArena Text: mathematical work | 1430 | 1305 | Claude Haiku 4.5 |
| MathArena | Not measured | 12.8% | Only gpt-oss-20b measured |
| Neither model has a result on the other 4 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index91
| Benchmark | Claude Haiku 4.5 | gpt-oss-20b | Leader |
|---|---|---|---|
| MMLU Pro | 78.7% | 71.6% | Claude Haiku 4.5 |
| LegalBench (Vals AI) | 81.2% | 70.8% | Claude Haiku 4.5 |
| CaseLaw (Vals AI) | 56.5% | 43.8% | Claude Haiku 4.5 |
| CorpFin (Vals AI) | 60.6% | 53.1% | Claude Haiku 4.5 |
| TaxEval (Vals AI) | 67.5% | 63.7% | Claude Haiku 4.5 |
| MortgageTax (Vals AI) | 62.2% | Not measured | Only Claude Haiku 4.5 measured |
| MedQA (Vals AI) | 79.6% | 82.9% | gpt-oss-20b |
| MedCode (Vals AI) | 32.7% | Not measured | Only Claude Haiku 4.5 measured |
| MMLU Pro (Artificial Analysis run) | Not measured | 74.8% | Only gpt-oss-20b measured |
| SimpleQA Verified | 13.2% | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: science | 1406 | 1296 | Claude Haiku 4.5 |
| LMArena Text: medicine and healthcare | 1394 | 1310 | Claude Haiku 4.5 |
| LMArena Text: legal and government | 1400 | 1280 | Claude Haiku 4.5 |
| LMArena Text: business and finance | 1400 | 1284 | Claude Haiku 4.5 |
| Neither model has a result on the other 6 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Haiku 4.5 | gpt-oss-20b | Leader |
|---|---|---|---|
| Design Arena: websites | 1122 | 852 | Claude Haiku 4.5 |
| Design Arena: UI components | 1097 | Not measured | Only Claude Haiku 4.5 measured |
| Design Arena: game dev | 1096 | Not measured | Only Claude Haiku 4.5 measured |
| Design Arena: data viz | 1124 | 933 | Claude Haiku 4.5 |
| Design Arena: 3D | 1071 | Not measured | Only Claude Haiku 4.5 measured |
| Design Arena: all code categories | 1114 | Not measured | Only Claude Haiku 4.5 measured |
| Design Arena: SVG | 1025 | Not measured | Only Claude Haiku 4.5 measured |
| Design Arena: ASCII art | 1140 | Not measured | Only Claude Haiku 4.5 measured |
| LiveBench design | 59.9% | Not measured | Only Claude Haiku 4.5 measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index180
| Benchmark | Claude Haiku 4.5 | gpt-oss-20b | Leader |
|---|---|---|---|
| LiveBench data analysis | 59.3% | Not measured | Only Claude Haiku 4.5 measured |
| Public Benefits Bench (Vals AI) | 54.3% | Not measured | Only Claude Haiku 4.5 measured |
| SAGE (Vals AI) | 31.8% | Not measured | Only Claude Haiku 4.5 measured |
| MedScribe (Vals AI) | 85.2% | Not measured | Only Claude Haiku 4.5 measured |
| Vals Multimodal Index | 42.9% | Not measured | Only Claude Haiku 4.5 measured |
| IFBench | Not measured | 65.1% | Only gpt-oss-20b measured |
| Long context reasoning (AA-LCR) | Not measured | 34.7% | Only gpt-oss-20b measured |
| DTBench | 73.6% | 68.0% | Claude Haiku 4.5 |
| LMCA | 30.9% | 14.5% | Claude Haiku 4.5 |
| ExploitBench | 13.7% | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text | 1397 | 1288 | Claude Haiku 4.5 |
| LMArena Text: instruction following | 1414 | 1236 | Claude Haiku 4.5 |
| LMArena Text: creative writing | 1371 | 1201 | Claude Haiku 4.5 |
| LMArena Text: English | 1414 | 1303 | Claude Haiku 4.5 |
| LMArena Text: non-English | 1377 | 1269 | Claude Haiku 4.5 |
| LMArena Text: Chinese | 1418 | 1315 | Claude Haiku 4.5 |
| LMArena Text: German | 1374 | 1255 | Claude Haiku 4.5 |
| LMArena Text: Japanese | 1338 | 1244 | Claude Haiku 4.5 |
| LMArena Text: Korean | 1346 | 1236 | Claude Haiku 4.5 |
| LMArena Text: French | 1411 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: Spanish | 1421 | 1267 | Claude Haiku 4.5 |
| LMArena Text: Russian | 1381 | 1278 | Claude Haiku 4.5 |
| LMArena Text: Polish | 1343 | 1252 | Claude Haiku 4.5 |
| LMArena Text: multi-turn | 1409 | 1268 | Claude Haiku 4.5 |
| LMArena Text: longer queries | 1427 | 1250 | Claude Haiku 4.5 |
| LMArena Text: writing and language | 1386 | 1238 | Claude Haiku 4.5 |
| LMArena Text: entertainment and media | 1369 | 1216 | Claude Haiku 4.5 |
| LMArena Document | 1420 | Not measured | Only Claude Haiku 4.5 measured |
| MultiChallenge | 50.5% | Not measured | Only Claude Haiku 4.5 measured |
| EQ-Bench 4 | 1064 | Not measured | Only Claude Haiku 4.5 measured |
| Neither model has a result on the other 18 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Haiku 4.5 | gpt-oss-20b | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
gpt-oss-20b costs less
Repository review
50K input + 3K output tokens
gpt-oss-20b costs less
Agent loop
200K input + 10K output tokens
gpt-oss-20b costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Anthropic Claude Haiku 4.5 | OpenAI gpt-oss-20b |
|---|---|---|
| Maker | Anthropic | OpenAI |
| Weights | No public weights listed | Open weights |
| Released | October 15, 2025 | August 5, 2025 |
| Context window | 200K | 131K |
| Input $/Mtok | $1.00 | $0.03 |
| Output $/Mtok | $5.00 | $0.15 |
| Coding index | 35.6 | Not benchmarked |
| Independent measurements behind it | 4 | 0 |
| Cost per solved task | $0.56 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Haiku 4.5 better than gpt-oss-20b for coding?
Only Claude Haiku 4.5 has a coding score, 35.6 on the Vibe Coding Index; gpt-oss-20b has none, so the two cannot be ranked on coding. Pick gpt-oss-20b for output tokens 33.3x cheaper ($0.15 vs $5.00 per million) and work measured by LiveCodeBench (Vals AI) or AIME, where it leads.
Which is cheaper, Claude Haiku 4.5 or gpt-oss-20b?
Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens; gpt-oss-20b costs $0.03 and $0.15. Cost per solved task is known for Claude Haiku 4.5 only.
Which has the bigger context window, Claude Haiku 4.5 or gpt-oss-20b?
Claude Haiku 4.5, with 200K tokens against 131K.
How many benchmarks is the Claude Haiku 4.5 vs gpt-oss-20b comparison based on?
47 benchmarks have a result for both models as of October 22, 2026. Claude Haiku 4.5's coding index rests on 4 independent benchmarks and gpt-oss-20b's on 0. Where only one model has a result, the page says so instead of naming a winner.