Across 17 comparable benchmarks, Claude Sonnet 4.5 has better reported results on 14 and worse on 2, with 1 tied. 1 further shared result is listed below, each with the reason it is not counted.
Moderate evidence17 of 18 shared results countedHow we compare
Price basis: Standard rates. The price section below shows the applicable periods.
| Fact | GPT OSS 120B | Claude Sonnet 4.5 |
|---|---|---|
| Context window | 128K tokens | 1M tokens |
| Input / 1M | $0.350 | $3.00 |
| Output / 1M | $0.750 | $15.00 |
| Blended (4:1) | $0.430 | $3.46 |
| Status | Available | Deprecated |
| Released | August 6, 2025 | September 30, 2025 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Mean of 8 shared benchmarks grouped by capability on a 0–100 scale. How averages are built
Claude Sonnet 4.5 ahead on 3 of 3 counted
Claude Sonnet 4.5 ahead on 1 of 1 counted
No fixed-scale average — see the rows in Benchmark results
Claude Sonnet 4.5 ahead on 1 of 1 counted
Split 1–1, 1 tied of 3 counted
Claude Sonnet 4.5 ahead on 1 of 1 counted
Claude Sonnet 4.5 ahead on 1 of 1 counted
Claude Sonnet 4.5 ahead on 2 of 3 counted
No shared comparable results for Research & search, Long context, Cybersecurity.
Published scores, with matching modes where available. Gaps show GPT OSS 120B relative to Claude Sonnet 4.5. Reading the results
| Benchmark | GPT OSS 120B | Claude Sonnet 4.5 | Gap |
|---|---|---|---|
| APEX-SWERepository Engineering · Pass@1 | 3.3Thinking High · tools | 31.0Thinking High · tools | −27.7 pts#61 vs #50 of 61 |
| SWE-bench VerifiedRepository Engineering · Accuracy | 60.1Thinking · no tools | 82.0≠Parallel Thinking · tools | −21.9 pts#78 vs #8 of 108 |
| Terminal Bench HardAgentic Development · Accuracy | 23.5Thinking High · tools | 35.6≠Thinking · tools | −12.1 pts#88 vs #47 of 157 |
| SimpleBenchCommonsense · Score (AVG@5) | 22.1Thinking · no tools | 54.3≠Normal · no tools | 0.41×#99 vs #58 of 106 |
| Vending-Bench 2Logical Planning · Money Balance (USD)Not counted · Speed and cost telemetry is reported, not scored | -21.5Unspecified Reasoning · tools | 3839Unspecified Reasoning · tools | —#62 vs #45 of 64 |
| AIME2025Mathematics · Accuracy | 97.9Thinking · tools | 100.0Thinking · tools | −2.1 pts#16 vs #1 of 86 |
| CritPtScientific Reasoning · Score | 1.1Thinking High · no tools | 1.1≠Thinking · no tools | =#103 vs #103 of 134 |
| GPQA DiamondScientific Reasoning · Accuracy | 80.1Thinking · no tools | 73.7≠Normal · no tools | +6.4 pts#111 vs #124 of 200 |
| SciCodeScientific Computing · Score | 34.0Thinking High · no tools | 45.7≠Thinking · no tools | 0.74×#88 vs #61 of 98 |
| Pinch BenchTool Orchestration · Accuracy | 60.6Thinking · tools | 88.2Thinking · tools | −27.6 pts#36 vs #5 of 38 |
| GDP.pdfDocuments & Charts · Task pass rate (%) | 4.0Thinking High · no tools | 5.2≠Thinking · no tools | −1.2 pts#77 vs #74 of 96 |
| Creative WritingWriting | 956Normal · no tools | 1677Normal · no tools | 0.57×#104 vs #36 of 121 |
| IF BenchInstruction Following · Accuracy | 69.0Normal · no tools | 57.3≠Thinking · tools | +11.7 pts#28 vs #33 of 38 |
| τ³-BankingService Workflows · Score | 12.8Thinking High · tools | 24.5≠Thinking · tools | 0.52×#83 vs #49 of 120 |
| HLEKnowledge Exams · Accuracy | 19.0Thinking · tools | 33.6Thinking · tools | −14.6 pts#107 vs #84 of 151 |
| MMLU-ProKnowledge Exams · Accuracy | 79.0Thinking · no tools | 88.0Thinking · no tools | −9.0 pts#65 vs #7 of 153 |
| ECICapability Indices · ECI score (capability index, higher is better) | 140Reported best | 147Reported best | 0.95×#97 vs #63 of 168 |
| LiveBenchCross-capability Suites · Accuracy | 46.1Normal · no tools | 68.2≠Thinking · no tools · 64K | −22.1 pts#100 vs #65 of 106 |
Repository Engineering · Pass@1
Repository Engineering · Accuracy
Agentic Development · Accuracy
Commonsense · Score (AVG@5)
Logical Planning · Money Balance (USD)
Not counted · Speed and cost telemetry is reported, not scored
Mathematics · Accuracy
Scientific Reasoning · Score
Scientific Reasoning · Accuracy
Scientific Computing · Score
Tool Orchestration · Accuracy
Documents & Charts · Task pass rate (%)
Writing
Instruction Following · Accuracy
Service Workflows · Score
A dash means no result is available.
| Benchmark | GPT OSS 120B | Claude Sonnet 4.5 |
|---|---|---|
| AIME 2024 | 96.6 | — |
| FrontierMath | — | 5.2 |
| FrontierMath - Tier 4 | — | 4.2 |
| FrontierMath Tier 4 v2 | — | 2.4 |
| FrontierMath v2 | — | 23.9 |
| MathArena Apex | 1.0 | — |
| MMLU | 90.0 | — |
| Aider-Polyglot | 41.8 | — |
| CodeClash | — | 1389 |
| CodeForces | 2622 | — |
| GSO | — | 14.7 |
| LiveCodeBench | 87.8 | — |
| SWE-Bench Pro - Public | — | 43.6 |
| Terminal Bench 2.0 | — | 42.8 |
| Terminal-Bench 1.0 | — | 50.0 |
| Vibe Code Bench v1.1 | — | 22.6 |
| WeirdML v2 | — | 47.7 |
| APEX-Agents | 4.4 | — |
| Claw Bench | — | 88.1 |
| MCP-Atlas | — | 59.5 |
| OSWorld-Verified | — | 62.9 |
| PinchBench v2 | 44.8 | — |
| AA Intelligence Index (historical versions) | 24.1 | — |
| AA Intelligence Index v5.0.1 | 3.8 | — |
| METR Time Horizons v1.1 | — | 122 |
| Text Arena (Coding) | — | 1391 |
| EBR-bench | — | 2.4 |
| GeoBench ACW | — | 60.0 |
| MMMU | — | 77.8 |
| MMMU-Pro | — | 68.9 |
| VPCT | — | 39.8 |
| AutomationBench | 0.15 | — |
| GDPval-AA | — | 39.0 |
| Harvey Lab-AA | 13.9 | — |
| SAGE | — | 36.1 |
| τ²-Bench | — | 84.7 |
| τ²-Bench - Telecom | — | 98.0 |
| ARC-AGI-1 | — | 63.7 |
| ARC-AGI-2 | — | 13.6 |
| BrowseComp | — | 24.1 |
| GAIA | — | 74.5 |
| MedCode | — | 44.1 |
| MedScribe | — | 84.5 |
Time-of-day providers use peak-hour rates; fixed-price providers use standard rates. Off-peak discounts remain in the published details.
Drag the handle above the bar for cache hits, the one below it for the input : output mix · 5% steps
Blended price = effective input rate at 90% cache hits × 80% + output rate × 20%
GPT OSS 120B costs88%lessthan Claude Sonnet 4.5 per million tokens — 8× cheaper.Using standard rates at this token mix.
GPT OSS 120B: Standard pricing. Cerebras Shared Inference official pricing (gpt-oss-120b) verified 2026-11-13
Claude Sonnet 4.5: Standard pricing. Anthropic official pricing (platform.claude.com/docs/en/about-claude/pricing) verified 2026-11-13; Deprecated 2026-09-30; tentative retirement 2026-11-30 (replacement: claude-sonnet-5-5)
| Price / 1M tokens | GPT OSS 120B | Claude Sonnet 4.5 | Ratio |
|---|---|---|---|
| Input | $0.35 | $3.00 | 0.12× |
| Output | $0.75 | $15.00 | 0.05× |
| Cached input | — | $0.30 | — |
| Cache write | — | — | — |
| Blended | $0.43 | $3.46 | 0.12× |
Estimates use the selected token mix. Cache writes, tool fees and long-context surcharges are excluded.
Reported cost per task, paired with the score from the same run. Settings and sources may differ; costs do not affect the verdict.
| Benchmark | GPT OSS 120B | Claude Sonnet 4.5 |
|---|---|---|
| AA Intelligence Index v5.0.1 | Not reported | |
| ARC-AGI-1 | Not reported | |
| ARC-AGI-2 | Not reported | |
| AutomationBench | $0.01 / task Average · Pass Rate: 0.15 Thinking High (With Tools) · zapier-private-heldout | Not reported |
| Attribute | GPT OSS 120B | Claude Sonnet 4.5 |
|---|---|---|
| Availability | Available | Deprecated |
| Provider | OpenAI | Anthropic |
| Model type | Reasoning model | Chat model |
| First release | August 6, 2025 | September 30, 2025 |
| Context window | 128K tokens | 1M tokens |
| Max output | 128K tokens | 64K tokens |
| Total parameters | 117B | — |
| Active parameters | 5.1B | — |
| Architecture | Mixture of Experts (MoE) | Undisclosed |
| Documented capabilities | Reasoning, Multilingual | Reasoning, Multilingual |
| Input modalities | Text | Text, Image |
| Output modalities | Text | Text |
| Weights | Open weights | Closed / API only |
| Licence | Apache 2.0 | — |
| Commercial use | Commercial use allowed | Proprietary |
These are reported-score comparisons, not controlled head-to-head tests.
What people found comparing these models, or using either one. Comments also appear on the models' own pages.
Used GPT OSS 120B or Claude Sonnet 4.5? Sign in with Google to share what worked, what did not, and which API or setup you tested.
No community comments on either model yet.
Alternatives with the most benchmark overlap for this matchup.