Claude Opus 5 vs gpt-oss-120b: Release Comparison
Comparison of the Claude Opus 5 and gpt-oss-120b releases: 5 and 2 models respectively, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across all 7 models.
- For intelligence, Claude Opus 5 scores highest: Claude Opus 5 (Adaptive Reasoning, Max Effort) at 51, against gpt-oss-120b (high) at 12 for gpt-oss-120b.
- For output speed, gpt-oss-120b is fastest: gpt-oss-120b (high) at 205 t/s, against Claude Opus 5 (Adaptive Reasoning, High Effort) at 50 t/s for Claude Opus 5.
- For cost per task, gpt-oss-120b is cheapest: gpt-oss-120b (high) at $0.11, against Claude Opus 5 (Adaptive Reasoning, Low Effort) at $1.10 for Claude Opus 5.
Releases compared
Intelligence
Artificial Analysis Intelligence Index
Intelligence Index vs. Cost per Intelligence Index Task
Cost
Cost per Intelligence Index Task
Speed & Latency
Output Speed
Capability Scores
Capability Indices
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, Humanity's Last Exam, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, Humanity's Last Exam, AA-LCR v1.1, GDP.pdf, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, MLCR-AA, Humanity's Last Exam, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, Humanity's Last Exam, CritPt, GDPval-AA v2, AA-Briefcase, Terminal-Bench 4.0 · Higher is better
Incorporates 5 evaluations: AA-Omniscience, Humanity's Last Exam, GDPval-AA v2, AA-Briefcase, AA-LCR v1.1 · Higher is better
Further details
Input modality | Output modality | Weights | Provider Benchmarks | ||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 5 (Adaptive Reasoning, Max Effort) |  Anthropic | 51 | 55 | 57 | 57 | 53 | 54 | 61 | $5.86 | $3.9 | $5.00 | $25.00 | $0.50 | $7,275 | 73k | 43k | 140M | 49 | 43.51s | 43.51s | 53.63s | 905.97s | - | 1M | Jul 2026 | - | Yes | Supports: text and image | Supports: text | Not available | - |   | |
| Claude Opus 5 (Adaptive Reasoning, Xhigh Effort) | Anthropic | 50 | 54 | 54 | 56 | 53 | 53 | 60 | $4.88 | $3.9 | $5.00 | $25.00 | $0.50 | $5,868 | 61k | 35k | 111M | 49 | 21.13s | 21.13s | 31.25s | 768.98s | - | 1M | Jul 2026 | - | Yes | Supports: text and image | Supports: text | Not available | - | | |
| Claude Opus 5 (Adaptive Reasoning, High Effort) | Anthropic | 48 | 52 | 54 | 55 | 52 | 52 | 58 | $3.61 | $3.9 | $5.00 | $25.00 | $0.50 | $4,332 | 46k | 25k | 81M | 50 | 9.28s | 9.28s | 19.33s | 574.39s | - | 1M | Jul 2026 | - | Yes | Supports: text and image | Supports: text | Not available | - | | |
| Claude Opus 5 (Adaptive Reasoning, Medium Effort) | Anthropic | 45 | 49 | 52 | 52 | 50 | 48 | 56 | $2.19 | $3.9 | $5.00 | $25.00 | $0.50 | $2,732 | 29k | 15k | 49M | 48 | 5.24s | 5.24s | 15.72s | 372.96s | - | 1M | Jul 2026 | - | Yes | Supports: text and image | Supports: text | Not available | - | | |
| Claude Opus 5 (Adaptive Reasoning, Low Effort) | Anthropic | 40 | 44 | 47 | 48 | 45 | 43 | 51 | $1.10 | $3.9 | $5.00 | $25.00 | $0.50 | $1,561 | 15k | 7k | 26M | 46 | 2.24s | 2.24s | 13.12s | 188.57s | - | 1M | Jul 2026 | - | Yes | Supports: text and image | Supports: text | Not available | - | | |
| gpt-oss-120b (high) |  OpenAI | 12 | 13 | 9 | 12 | 12 | 16 | 19 | $0.11 | $0.2 | $0.15 | $0.595 | $0.125 | $122 | 27k | 15k | 84M | 205 | 0.84s | 10.58s | 13.01s | 130.69s | 117B 5.1B active at inference time | 131k | Aug 2025 | May 2024 | Yes | Supports: text | Supports: text |    +14 | |||
| gpt-oss-120b (low) | OpenAI | 10 | - | - | - | - | - | - | - | $0.2 | $0.15 | $0.545 | $0.15 | - | - | - | - | 202 | 0.84s | 10.71s | 13.18s | - | 117B 5.1B active at inference time | 131k | Aug 2025 | May 2025 | Yes | Supports: text | Supports: text |    +14 | |||