Anthropic claims its new Claude Opus 5 delivers near-Fable 5 performance at half the token price

Anthropic claims its new Claude Opus 5 delivers near-Fable 5 performance at half the token price

Key Points

- Anthropic is positioning Claude Opus 5 as a cheaper alternative to Fable 5 that beats it in several benchmarks.

- Opus 5 leads tests in agentic coding and knowledge work. On ARC-AGI-3, which measures novel problem-solving, the model scores 30.2 percent, nearly four times higher than GPT-5.6 Sol.

- Anthropic says Opus 5 can check and improve its own work through iteration, and build its own tools through code when it needs them.

Anthropic's new flagship model Claude Opus 5 posts top scores in coding and knowledge work while approaching Claude Fable 5's performance at half its token rates.

Anthropic is responding to pricing pressure from GPT-5.6 Sol and Chinese competitors. Its new Opus 5 model is designed to close the price-performance gap with the much pricier Fable 5. Opus 5 becomes the default model on Claude Max and the most capable model available on Claude Pro.

The 1 million-token context window and token rates remain unchanged. Like its predecessor Opus 4.8, Opus 5 costs $5 per million input tokens and $25 per million output tokens. A new Fast Mode increases speed by 2.5x but doubles the price.

But token rates don't tell the full story without factoring in token efficiency. Opus 4.7 ended up costing 30 to 40 percent more per task than Opus 4.6, even though both models had the same base rates. A similar pattern showed up recently with Claude Sonnet 5.

Higher effort can cost more and perform worse

Users can trade off performance against token use through five effort settings called low, medium, high, xhigh, and max. Anthropic says Opus 5 offers better value than its predecessor at every effort level.

In its prompting guide, Anthropic recommends making broad use of the "low" and "medium" settings. The company says they deliver good results with a fraction of the token use and latency while beating the same settings on earlier Opus models. For coding and agentic tasks, Anthropic still recommends starting with "xhigh."

Opus 5 scores slightly worse at the max effort setting than at the second-highest setting on two benchmarks, despite costing more. The drop appears on Frontier-Bench v0.1 and the Artificial Analysis Coding Agent Index.

Opus 5 beats Fable 5 at agentic coding

According to Anthropic's own benchmarks, Opus 5 sets records across several evaluations. On Frontier-Bench v0.1, the model hits 43.3 percent on agentic terminal coding, beating Fable 5 (33.7 percent), GPT-5.6 Sol (34.4 percent), and its predecessor Opus 4.8 (21.1 percent) by wide margins. On the knowledge work benchmark GDPval-AA v2, Opus 5 leads with an Elo score of 1,861, ahead of Fable 5 (1,747) and GPT-5.6 Sol (1,736).

Opus 5 doesn't win everywhere. On agentic coding via DeepSWE v1.1, GPT-5.6 Sol leads with 72.7 percent, followed by Fable 5 (69.7 percent) and Opus 5 (68.8 percent). On health tasks and legal benchmarks, Fable 5 and Mythos 5 outperform Opus 5, respectively.

The ARC-AGI-3 result is likely the biggest surprise and outlier in Anthropic's benchmarks. The benchmark measures novel problem-solving without memorized patterns, and Opus 5 scores 30.2 percent. Opus 4.8 managed just 1.5 percent, GPT-5.6 Sol hit 7.8 percent. That's nearly a 4x gap over the next-best model. There's no Fable 5 result for this benchmark, and it's unclear whether such a large lead on a test will show up in actual use.

Opus 5 falls behind Mythos 5 on cybersecurity tasks. Anthropic says it deliberately didn't train Opus 5 on cyber tasks, as was also the case with its predecessor. The model comes close to Mythos 5 at finding vulnerabilities but performs much worse when asked to exploit them.

Anthropic also says Opus 5 has improved at generating visual outputs and analyzing visual content such as charts and diagrams.

Opus 5 builds its own tools when it needs them

Anthropic describes Opus 5 as much better at checking its own work and improving it through iteration. In a Frontier-Bench task, Opus 5 received a drawing of a machine part and had to create a 3D model in FreeCAD. The catch was that the model intentionally had no way to view the drawing directly. Opus 5 responded by writing its own computer vision pipeline to extract the geometry from raw pixels, then reconstructed the complete machine part. No other model solved this task after five attempts, Anthropic says.

Opus 5 also worked on a real bug in a popular open-source package manager. According to Anthropic, it found the root cause and fixed an edge case that the community patch had missed. A competing model fixed only the surface symptom before reporting the bug as resolved.

An engineer at a trading firm reportedly used Opus 5 to build a market data feed for a new exchange in one session. Previous models couldn't complete the task, even with detailed plans.

Opus 5's cyber filters trigger less often than Fable 5's

Opus 5's safety setup allows source code vulnerability research but blocks binary-based vulnerability scanning, penetration testing, and exploit generation, according to Anthropic. The cyber classifiers trigger about 85 percent less often than on Fable 5. Fable 5's frequent interventions drew heavy criticism. Blocked requests in Claude.ai, Claude Code, and Claude Cowork default to Opus 4.8 as a fallback, the same approach used with Fable 5.

Anthropic calls Opus 5 the most capable generally available model for scientific research. It shows gains over Opus 4.8 across all life sciences evaluations, with standout improvements in organic chemistry (plus 10.2 percentage points on deriving molecular structures from spectroscopy data) and protein-related tasks (plus 7.7 percentage points).

Alongside Opus 5, Anthropic is releasing two beta features. Mid-Conversation Tool Changes on the Claude Platform let developers swap available tools during a conversation without invalidating the prompt cache. Automatic Fallbacks on the API route blocked requests to a different model automatically.

AI News Without the Hype – Curated by Humans

Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.

Subscribe now