head-to-head
| Metric | Kimi K3 | Claude Opus 4.8 |
|---|---|---|
| SWE-bench Verified | 93.4% | 88.6% |
| SWE-bench Pro | — | 69.2% |
| Terminal-Bench | 88.3% | ~82.7% (TB2.1) |
| Input $ / 1M | $3 | $5 |
| Output $ / 1M | $15 | $25 |
| Context | 1M | 1M |
| Open weights | Yes | No |
| Access | API · app · open weights promised Jul 27, 2026 | API · Claude Code · claude.ai (Max) |
| Maker | Moonshot AI | Anthropic |
what do the benchmarks actually say?
On SWE-bench Verified — real, human-validated GitHub issues resolved end-to-end — Kimi K3 posts 93.4% against 88.6% for Claude Opus 4.8, a 4.8-point gap. Verified is the closest public proxy for "can it fix a real bug in a real repo without help", which is why it anchors our ranking.
A few points either way is real but not decisive: within that band, the agent scaffolding around the model — how it retrieves files, runs tests, and retries — often matters as much as the base model. Treat the gap as a lean, not a verdict.
which is cheaper to run?
Kimi K3 is the cheaper model: $3 per 1M input tokens ($15 output) versus $5 ($25 output) for Claude Opus 4.8 — roughly 1.7× less on input. Coding workloads are output-heavy — agents write diffs, tests and retries — so weight the output rate more than the input rate when you estimate a monthly bill.
Kimi K3 ships open weights. Beyond the per-token discount, that means you can self-host it, fine-tune it, pin a snapshot so the model can't change under you, and keep code on your own infrastructure — none of which is possible with Claude Opus 4.8, which is API-only. For teams with compliance constraints that difference outweighs any benchmark point.
when to pick each
The highest-scoring open-weight model on the board and the largest ever announced (2.8T MoE, 16 of 896 experts active): frontier-adjacent coding you can eventually self-host, at a third of Fable 5's price.
The hardest agentic refactors and long, autonomous multi-file tasks where every point of accuracy saves a human review cycle.
how were these scores verified?
We only print a number once it's confirmed against a primary source or an independent evaluation, and each row on our leaderboard records which kind it is:
- Kimi K3: Independent (vals.ai, mini-swe-agent bash-only harness): SWE-bench Verified 93.40% ±1.11. Verified Jul 18, 2026 — vals.ai had not run K3 at our Jul 17 check and now ranks it third overall (above GPT-5.6 Luna at 93.0% and Claude Opus 4.8 at 88.6%), making it the highest-scoring open-weight coder we track. Moonshot published no SWE-bench Verified score of its own, only Terminal-Bench 2.1 88.3% on its KimiCode harness, so we rank on the independent number per our standing rule. Also 3rd on Artificial Analysis GDPval-AA v2 and 2nd on AA-Briefcase. Price: Moonshot API $3/$15 per 1M (cache-hit input $0.30); open weights promised Jul 27, 2026.
- Claude Opus 4.8: Independent (vals.ai, Jul 14 2026, mini-swe-agent bash-only harness): SWE-bench Verified 88.6% ±1.42. Corrected Jul 17, 2026: we previously printed Anthropic's own "~86%" and claimed independent evals tracked it within ~1 point, which was wrong — the independent number is 2.6 points higher, and our methodology is to prefer the independent one. Run through the Claude Code harness instead of the bare bash agent, vals.ai measures 85.8%, a reminder that the harness moves these numbers as much as the model does. SWE-bench Pro 69.2% is Anthropic-reported.
Full reviewsKimi K3, decoded
Ranked on our AI Coding Leaderboard, updated 2026-07-18. Scores are confirmed against primary sources; prices are per 1M input tokens and can change.
- Moonshot AIvals.ai — SWE-bench Verified (independent) — Independent (vals.ai, mini-swe-agent bash-only harness): SWE-bench Verified 93.40% ±1.11. Verified Jul 18, 2026 — vals.ai had not run K3 at our Jul 17 check and now ranks it third overall (above GPT-5.6 Luna at 93.0% and Claude Opus 4.8 at 88.6%), making it the highest-scoring open-weight coder we track. Moonshot published no SWE-bench Verified score of its own, only Terminal-Bench 2.1 88.3% on its KimiCode harness, so we rank on the independent number per our standing rule. Also 3rd on Artificial Analysis GDPval-AA v2 and 2nd on AA-Briefcase. Price: Moonshot API $3/$15 per 1M (cache-hit input $0.30); open weights promised Jul 27, 2026.
- Anthropicvals.ai — SWE-bench Verified (independent) — Independent (vals.ai, Jul 14 2026, mini-swe-agent bash-only harness): SWE-bench Verified 88.6% ±1.42. Corrected Jul 17, 2026: we previously printed Anthropic's own "~86%" and claimed independent evals tracked it within ~1 point, which was wrong — the independent number is 2.6 points higher, and our methodology is to prefer the independent one. Run through the Claude Code harness instead of the bare bash agent, vals.ai measures 85.8%, a reminder that the harness moves these numbers as much as the model does. SWE-bench Pro 69.2% is Anthropic-reported.
- BenchmarkSWE-bench — the real-GitHub-issue benchmark