Claude Opus 5 vs GPT-5.6 Sol
Claude Opus 5 comes out ahead on 9 of 14 shared measures, and the two rank 4 and 12 of 51 overall. GPT-5.6 Sol is 1.3× cheaper per million tokens (blended) — A$19.65 vs A$24.57 per 1,000 replies of customer support replys.
Where each one wins.
Claude Opus 5 ranks 4th of 51; GPT-5.6 Sol ranks 12th.
Claude Opus 5 ranks 3rd of 42; GPT-5.6 Sol ranks 7th.
Claude Opus 5 ranks 3rd of 41; GPT-5.6 Sol ranks 6th.
Claude Opus 5 ranks 4th of 51; GPT-5.6 Sol ranks 7th.
GPT-5.6 Sol ranks 6th of 51; Claude Opus 5 ranks 19th.
Claude Opus 5 ranks 18th of 50; GPT-5.6 Sol ranks 22nd.
GPT-5.6 Sol is 1.3× cheaper per million tokens (blended) — A$19.65 vs A$24.57 per 1,000 replies of customer support replys.
GPT-5.6 Sol writes 1.2× faster (62 tok/s vs 51 tok/s).
Both can be used from Australia through their makers’ own APIs (Anthropic and OpenAI), which may process requests outside Australia. Claude Opus 5 can run with requests kept in Australia on AWS Bedrock in Sydney and Melbourne. GPT-5.6 Sol can be called from AWS Bedrock in Sydney and Melbourne and Microsoft Azure in Australia East, but only through global routing, so requests may be processed outside Australia.
Side by side.
“Level” means the gap is inside LMArena’s confidence interval, or the scores are identical. Independent test scores are for each model’s headline setting. Both models can be used from Australia through their makers’ APIs; the Australian rows show whether requests can also be processed in Australia.
| BENCHMARK | CLAUDE OPUS 5 | GPT-5.6 SOL | LEADS |
|---|---|---|---|
| AA Intelligence Index | 50.8 | 47.0 | Claude Opus 5 |
| AA Coding Index | 78.0 | 77.4 | Claude Opus 5 |
| GPQA Diamond | 93.2% | 94.1% | GPT-5.6 Sol |
| Humanity’s Last Exam | 54.9% | 49.5% | Claude Opus 5 |
| AA-LCR | 79.3% | 84.0% | GPT-5.6 Sol |
| Terminal-Bench 2.1 | 89.1% | 88.0% | Claude Opus 5 |
| τ²-Bench (banking) | 42.1% | 44.3% | GPT-5.6 Sol |
| SciCode | 56.4% | 57.1% | GPT-5.6 Sol |
| LMArena Text | 1493 | 1484 | Claude Opus 5 |
| LMArena WebDev | 1691 | 1617 | Claude Opus 5 |
| LMArena Vision | 1289 | 1286 | Level |
| LMArena Document | 1490 | 1489 | Level |
| LMArena Search | 1256 | ||
| LMArena Agent | #3 | #7 | Claude Opus 5 |
| Blended price (AUD) | A$14.04 | A$11.23 | GPT-5.6 Sol |
| Output speed | 51 tok/s | 62 tok/s | GPT-5.6 Sol |
| Answer starts after | 34 s | 1.0 min | Claude Opus 5 |
| Context window | 1,000,000 tokens | 1,050,000 tokens | GPT-5.6 Sol |
| USE FROM AUSTRALIA | |||
| Maker’s API | YES | YES | |
| Processed in Australia | YES · CLOUD | NO | |
| AUSTRALIAN CLOUD REGIONS | |||
| AWS Bedrock · Sydney | AU ROUTING | GLOBAL | |
| AWS Bedrock · Melbourne | IN REGION | GLOBAL | |
| Azure · Australia East | NOT IN AU | GLOBAL | |
| Google Vertex AI · Sydney | GLOBAL | NOT OFFERED | |
The same jobs, in Australian dollars.
List prices at the snapshot’s RBA rate, excluding GST and reasoning tokens.
| JOB | CLAUDE OPUS 5 | GPT-5.6 SOL | MEDIAN MODEL |
|---|---|---|---|
| Customer support replyPER 1,000 REPLIES | A$24.57 | A$19.65 | ≈ A$6.58 |
| Summarise a 30-page documentPER 100 DOCUMENTS | A$16.85 | A$13.48 | ≈ A$4.74 |
| Agentic coding taskPER 10 TASKS | A$13.34 | A$10.67 | ≈ A$3.72 |
Each model in full.
Claude Opus 5 or GPT-5.6 Sol?
Is Claude Opus 5 better than GPT-5.6 Sol?
On our overall leaderboard Claude Opus 5 ranks 4th and GPT-5.6 Sol 12th of 51. Which is better depends on the job: the table above compares each benchmark, price and Australian availability.
Which is cheaper, Claude Opus 5 or GPT-5.6 Sol?
GPT-5.6 Sol, at A$11.23 per million tokens (blended) against A$14.04 for Claude Opus 5. Reasoning-heavy settings add output tokens, so real bills depend on the effort level you run.
Can I use Claude Opus 5 and GPT-5.6 Sol in Australia?
Both can be used from Australia through their makers’ own APIs (Anthropic and OpenAI), which may process requests outside Australia. Claude Opus 5 can run with requests kept in Australia on AWS Bedrock in Sydney and Melbourne. GPT-5.6 Sol can be called from AWS Bedrock in Sydney and Melbourne and Microsoft Azure in Australia East, but only through global routing, so requests may be processed outside Australia.
Ratings: LMArena leaderboard dataset (CC BY 4.0), rescaled for the lens scores · leaderboards to 22 Sep 2026
Evaluations, prices and speed: Artificial Analysis (artificialanalysis.ai) · fetched 23 Sep 2026
Exchange rate: Reserve Bank of Australia, table F11.1 · A$1 = US$0.7123 on 22 Sep 2026 · prices exclude GST
Snapshot 23 Sep 2026 · updated weekly · How the rankings work →