Loading benchmark catalogue
Compare performance benchmarks, coding intelligence, reasoning evaluations, context limits, and API economics between Claude Opus 4.8 (Anthropic) and GPT-6.1 Sol (OpenAI).
| Metric / Capability | Claude Opus 4.8 | GPT-6.1 Sol |
|---|---|---|
| Developer / Organization | Anthropic | OpenAI |
| Release Date | 2026-05-27 | 2026-09-29 |
| Deployment / Weights | Proprietary Cloud API | Proprietary Cloud API |
| Context Window | 1M tokens (1,000,000 tokens) | 1.1M tokens (1,050,000 tokens) |
| Input Pricing (/1M Tokens) | $5 | $2 |
| Output Pricing (/1M Tokens) | $25 | $10 |
| Benchmark / Domain | Claude Opus 4.8 | GPT-6.1 Sol | Advantage |
|---|---|---|---|
Artificial Analysis Intelligence Index Composite index aggregating 10+ evaluations of general reasoning and knowledge. | 41.8% | 51.8% | GPT-6.1 Sol (+24%) |
Artificial Analysis Coding Index Composite index of coding and software-engineering evaluations. | 74.3% | — | — |
Artificial Analysis Agentic Index Composite index of tool-use and long-horizon agentic tasks. | 41.9% | — | — |
Artificial Analysis Coding Agent Index v2.0 Composite index of coding-agent systems (model + harness) across FrontierCode v1.1, SWE-Atlas-QnA, and Terminal-Bench v4. | — | 54.1% | — |
SWE-bench Pro Harder, contamination-resistant successor to SWE-bench spanning multiple languages. | 69.2% | — | — |
Terminal-Bench 4.0 Sandboxed command-line tasks requiring shell and file-system operation. | 23.6% | 58.2% | GPT-6.1 Sol (+147%) |
ARC-AGI-2 Novel visual grid puzzles requiring abstract rule induction. | 72.1% | 94.2% | GPT-6.1 Sol (+31%) |
GPQA Diamond Graduate-level physics, chemistry, and biology questions written by domain experts. | 93.6% | — | — |
Humanity's Last Exam Expert-written questions across hundreds of disciplines designed to resist saturation. | 49.8% | — | — |
FrontierMath v2 (Tiers 1-3) Unpublished, research-level mathematics problems across Tiers 1-3. | 80.0% | 93.7% | GPT-6.1 Sol (+17%) |
Design Arena ELO Human-preference ELO across UI, 3D, data-visualization, and game-dev generations. | 1310 | 1437 | GPT-6.1 Sol (+10%) |
GPT-6.1 Sol outperforms Claude Opus 4.8 across 5 evaluated benchmarks compared to 0 for Claude Opus 4.8, excelling in Artificial Analysis Intelligence Index, Terminal-Bench 4.0, ARC-AGI-2.
GPT-6.1 Sol has the larger context capacity of 1.1M tokens (1,050,000 tokens), compared to 1M tokens for Claude Opus 4.8.
GPT-6.1 Sol is more economical. Input tokens cost $2/M tokens compared to $5/M tokens for Claude Opus 4.8.
Claude Opus 4.8 is a proprietary cloud API. GPT-6.1 Sol is a proprietary cloud API.
Analyze 130+ models side-by-side using interactive radar charts, cost-efficiency quadrant plots, and live dataset filters on the full NeuBench index.
Open Interactive Comparator